###

DOI:

计算机系统应用英文版:2011,20(1):178-

View/Add Comment 过刊浏览高级检索 HTML

←前一篇 | 后一篇→

码上扫一扫！

下载全文

GPU 上的矩阵乘法的设计与实现

梁娟娟, 任开新, 郭利财, 刘燕君

(中国科学技术大学计算机科学与技术学院，合肥 230027)

Design and Implementation of Matrix Multiplication on GPU

LIANG Juan-Juan, REN Kai-Xin, GUO Li-Cai, LIU Yan-Jun

(School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China)

摘要

图/表

参考文献

相似文献

本文已被：浏览 2603次下载 7924次
Received:April 26, 2010 Revised:May 21, 2010

中文摘要: 矩阵乘法是科学计算中最基本的操作，高效实现矩阵乘法可以加速许多应用。本文使用NVIDIA 的CUDA在GPU 上实现了一个高效的矩阵乘法。测试结果表明，在Geforce GTX 260 上，本文提出的矩阵乘法的速度是理论峰值的97%，跟CUBLAS 库中的矩阵乘法相当。

中文关键词: 矩阵乘法 GPU CUDA

Abstract:Matrix multiplication is a basic operation in scientific computing. Efficient implementation of matrix multiplication can speed up many applications. In this paper, we implement an efficient matrix multiplication on GPU using NVIDIA’s CUDA. The experiment shows that our implementation is as fast as the implementation in CUBLAS, and the speed of our implementation can reach the peak speed’s 97%, on Geforce GTX260.

keywords: matrix multiplication GPU CUDA

文章编号： 中图分类号： 文献标志码：

基金项目:基金项目:国家自然科学基金(60833004);国家高技术研究发展计划(863)(2008AA010902)

引用文本：
梁娟娟,任开新,郭利财,刘燕君.GPU 上的矩阵乘法的设计与实现.计算机系统应用,2011,20(1):178-
LIANG Juan-Juan,REN Kai-Xin,GUO Li-Cai,LIU Yan-Jun.Design and Implementation of Matrix Multiplication on GPU.COMPUTER SYSTEMS APPLICATIONS,2011,20(1):178-

Author Name	Affiliation
LIANG Juan-Juan	School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China
REN Kai-Xin	School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China
GUO Li-Cai	School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China
LIU Yan-Jun	School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China