Heterogeneous Parallel and Distributed Optimization of K-Means Algorithm on Sunway Supercomputer.

ISPA/IUCC(2017)

引用 2|浏览14
暂无评分
摘要
Clustering plays an essential role in large-volume data analysis areas such as bioinformatics, statistic, pattern recognition and so on. K-means is one of most effective clustering algorithms, which is relatively easy to implement. Most real world applications usually involve a huge amount of data. Thus, how to improve applicationsu0027 efficiency while maintaining accuracy becomes a significant and considerable issue. In this paper, a K-means clustering algorithm, which uses heterogeneous parallel computing technology on Computing processing elements and distributed computing technology, is proposed. This algorithm is applied in unique architecture based on Sunway TaihuLight Supercomputer---the worldu0027s fastest supercomputer with peak performance over 100PFLOPS. The testing results suggest that this improved algorithm is stable, fast and efficient. Conclusively, it has a great improvement in computation performance, especially with large volumes of data.
更多
查看译文
关键词
computing processing element,processing element,core group,management processing element,data point,sunway architecture,cluster center,sunway cpu,mpi double,big data,sunway taihulight,heterogeneous parallel computing,computing new centroid,closest centroid,clustering algorithm,time efficiency,distributed computing,big data analysis,cluster center information,thread group,mpi send,master core,processing core
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要