计算机工程与应用2011，Vol.47Issue(19)：9-11,23,4.DOI:10.3778/j.issn.1002-8331.2011.19.003
CPU与GPU上几种矩阵乘法的比较与分析
Comparison and analysis of matrix multiplications on GPU and CPU
摘要
Abstract
Three matrix multiplications on CPU and four CUDA-based matrix multiplications on GPU are described, the causes of high performance are analyzed and the common characteristic of efficient algorithm is that data are properly organized and rationally utilized,and therefore the access cost effectively reduced and the speed is greatly improved.The best optimized implementation on CPU gain more 200 times fast than the common one,the best optimized implementation on GPU gain about 6 times fast than the best one on CPU.关键词
矩阵乘法/统一计算设备架构/图形处理器/存储模式Key words
matrix multiplication/ Compute Unified Device Architecture (CUDA)/ Graphic Processing Unit (GPU)/ storage pattern引用本文复制引用
刘进锋,郭雷..CPU与GPU上几种矩阵乘法的比较与分析[J].计算机工程与应用,2011,47(19):9-11,23,4.基金项目
宁夏高等学校科学技术研究项目 （）
