首页 | 官方网站   微博 | 高级检索  
     

水动力学数学模型并行计算技术研究及实现
引用本文:杨明,余欣,姜恺,高文永.水动力学数学模型并行计算技术研究及实现[J].泥沙研究,2007(3):1-3.
作者姓名:杨明  余欣  姜恺  高文永
作者单位:1. 天津大学,天津,300072;黄河水利科学研究院,河南,郑州,450003
2. 黄河水利科学研究院,河南,郑州,450003
3. 上海超级计算中心,上海,201203
4. 黄河水利委员会山东水文水资源局,山东,济南,250100
基金项目:国家自然科学基金委员会、水利部黄河水利委员会联合研究基金
摘    要:基于MPI(Message Passing Interface)消息传递实现了黄河二维水动力学数学模型的并行编程。以数据的分布存储作为区域划分的依据,实现了计算量的负载平衡;在全局网格和局部区域之间建立映射关系,并且在临界单元、进出口单元、共用节点等通过规约等进行特殊处理,一方面尽可能的减少通讯量,另一方面也避免消息的阻塞。采用曙光4000A系统的8个CPU进行计算的加速比达0.8,多CPU并行计算极大的提高了计算任务的容量,使得无法在单机上完成的巨量计算成为可能。

关 键 词:并行计算  通讯  规约  加速比
文章编号:0468-155X(2007)03-0001-03
修稿时间:2006-10-25

Research and application of parallel computing technology on hydrodynamic model
YANG Ming,YU Xin,JIANG Kai,GAO Wen-yong.Research and application of parallel computing technology on hydrodynamic model[J].Journal of Sediment Research,2007(3):1-3.
Authors:YANG Ming  YU Xin  JIANG Kai  GAO Wen-yong
Affiliation:1. Tianjin University, Tianfin, 300072 ; 2. Yellow River Institute of Hydraulic Research, YRCC, Zhengzhou 450003 3. Shanghai Super Computing Center, Shanghai 201203; 4. Shandong Hydrology Bureau of YRCC, Jinan 250100
Abstract:Parallel program design of Yellow River flow-sediment model was realized based on MPI(Message Passing Interface).Load balance of computing quantity was realized through regional division according to distributive storage of data. The mapping relation between whole grids and part-region was established.Special treatments were made at critical units through protocols,input & output units and shared nodes.These treatments can decrease communication as much as possible and avoid information-jam.The parallel program can meet the demands of computing capacity and speed in the Yellow River flow-sediment mathematical model.
Keywords:MPI
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号