Optimized data I/O strategy of the algorithm of parallel digital terrain analysis

被引：20

作者：

Li, Yan ^{[1
]}

Dou, Wanfeng ^{[2
]}

Yang, Kun ^{[1
]}

Miao, Shoushuai ^{[1
]}

机构：

[1] Nanjing Normal Univ, Nanjing, Jiangsu, Peoples R China

[2] Nanjing Normal Univ, Informat Secur Technol & Engineer Res Ctr Jiangsu, Nanjing, Jiangsu, Peoples R China

来源：

PROCEEDINGS OF THIRTEENTH INTERNATIONAL SYMPOSIUM ON DISTRIBUTED COMPUTING AND APPLICATIONS TO BUSINESS, ENGINEERING AND SCIENCE, (DCABES 2014) | 2014年

基金：

中国国家自然科学基金;

关键词：

the parallel pipeline; the asynchronous data I/O; the parallel computation; the digital terrain analysis;

D O I：

10.1109/DCABES.2014.10

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In order to improve the analysis performance of the algorithm of parallel digital terrain analysis, a series of parallel tasks should be proceed by the appropriate partition and scheduling strategy, but the algorithm of data I/O strategy can also be optimized. Based on the conventional data I/O model, the DEM data I/O strategy of the parallel algorithm for digital terrain can be optimized by the parallel pipeline method. Then it can further enhance the efficiency of the parallel algorithm of digital terrain analysis. Take the maximum slope algorithm for example, it was conducted many experiments in the small-scale cluster environment. The results show that the parallel algorithm based on the optimized data I/O strategy can improve the analysis efficiency of the previously conventional algorithm.

引用

页码：34 / 37

页数：4