| 基于MPI的并行Kriging空间降水插值 |
| |
| 引用本文： | 白树仁,李涛,宁锦阳. 基于MPI的并行Kriging空间降水插值[J]. 计算技术与自动化, 2011, 30(1): 71-74 |
| |
| 作者姓名： | 白树仁 李涛 宁锦阳 |
| |
| 作者单位： | 1. 湖南大学,高性能计算中心,湖南,长沙,410082
2. 湖南大学,信息科学与工程学院,湖南,长沙,410082 |
| |
| 基金项目： | 国家气象局的"精细化农业区划试点"项目、湖南省科技计划重大专项资助 |
| |
| 摘 要： | 为减少空间降水插值的计算时间,以MPI并行接口为技术手段,采用数据划分建模方法,实现改进Kriging算法的并行算法.在Linux操作系统上搭建并行计算环境,试验数据表明,该并行算法能有效节省计算时间并具有良好的加速比、并行效率和扩展性.为Kriging插值算法的并行化实现和应用提供有意义的参考.
|
| 关 键 词： | 并行计算 MPI Kriging |
Parallel Kriging on Interpolation of Spatial Precipitation Based on MPI |
| |
| BAI Shu ren,LI Tao,NING Jin yang. Parallel Kriging on Interpolation of Spatial Precipitation Based on MPI[J]. Computing Technology and Automation, 2011, 30(1): 71-74 |
| |
| Authors: | BAI Shu ren LI Tao NING Jin yang |
| |
| Affiliation: | 1.High Performance Computing Center,Hunan University,Changsha 410082,China;2.College of Information Science and Engineering,Hunan University,Changsha 410082,China) |
| |
| Abstract: | In order to improve the calculation speed for interpolation of Spatial Precipitation（SP）,using MPI parallel interface library and modeling approach using data partitioning,achieve parallel Kriging algorithm for interpolation of SP.The parallel computing environment is based on the Linux operating system.Experimental results show that the parallel algorithm can effectively save computing time and has a good Speedup,parallel efficiency and scalability.It also provides a meaningful reference for the parallel implementation and application of Kriging interpolation algorithm. |
| |
| Keywords: | MPI Kriging |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算技术与自动化》浏览原始摘要信息 |
|
点击此处可从《计算技术与自动化》下载全文 |
|
