计算机工程与应用2012，Vol.48Issue(2)：201-202,226,3.DOI:10.3778/j.issn.1002-8331.2012.02.058
GPU上实现的向量点积的性能分析
Performance analysis of vector dot product on GPU
摘要
Abstract
CUDA is a convenient use of GPU for general computing. This paper researches several vector dot product algorithms based on CUDA, comparison and analysis of their performances and causes. Experiment shows that the best algorithm is faster than the CPU algorithm for about 7 times.关键词
统一设备计算架构(CUDA)/图形处理器(GPU)/向量点积Key words
Compute Unified Device Architecture (CUDA)/ Graphic Processing Unit (GPU)/ vector dot product分类
信息技术与安全科学引用本文复制引用
郭雷,刘进锋..GPU上实现的向量点积的性能分析[J].计算机工程与应用,2012,48(2):201-202,226,3.基金项目
宁夏高等学校科学研究项目资助. （）
