引用本文: | 陈军,王正华,李晓梅.高阶稠密矩阵的并行求逆与应用[J].国防科技大学学报,1997,19(4):1-4.[点击复制] |
Chen Jun,Wang Zhenghua,Li Xiaomei.Parallel High-order Dense Matrix Inversion and Applications[J].Journal of National University of Defense Technology,1997,19(4):1-4[点击复制] |
|
|
|
本文已被:浏览 7141次 下载 6108次 |
高阶稠密矩阵的并行求逆与应用 |
陈军, 王正华, 李晓梅 |
(并行与分布处理国家重点实验室 湖南 长沙 410073)
|
摘要: |
采用基于列交换的Gauss-Jordan 并行算法来解决空气动力学中超音速高阶面元法的稠密矩阵求逆问题, 该方法采取了块循环数据分配方式, 尤其对超立方体结构的并行机系统来说具有通讯优势。在4 台SGI 工作站构成的2×2 网格上进行的实验表明, 对秩为1000 左右的矩阵可得到57%~64%的效率。 |
关键词: 超音速流, 高阶面元法, 矩阵求逆, Gauss-Jordan 算法, SGI工作站 |
DOI: |
投稿日期:1996-11-14 |
基金项目:国家自然科学基金和863计划基金资助项目 |
|
Parallel High-order Dense Matrix Inversion and Applications |
Chen Jun, Wang Zhenghua, Li Xiaomei |
(P&DP National Laborary, Changsha, 410073)
|
Abstract: |
In this paper we propose Gauss-Jordan algorithm using column interchanges for computing a high-order dense matrix inverse produced by the high-order panel method in aerodynamics. The algorithm implements the block cyclic data distribution, which especially has communication advantages for the hypercube network. Results are achieved when running this program on the 4 SGI workstations configured as a 2×2 processor grid. It shows that 57%~64% efficiency can be gained when solving a matrix is about 1000 order. |
Keywords: supersonic flow, high-order panel method, matrix inversion, Gauss-Jordan algorithm, SGI |
|
|
|
|
|