首页 | 本学科首页   官方微博 | 高级检索  
     

使用CUDA平台关于并行高斯-约当消去法的研究与比较
引用本文:毛飞,陈智骏,梁效斐,曹奇英. 使用CUDA平台关于并行高斯-约当消去法的研究与比较[J]. 计算机应用与软件, 2011, 0(9)
作者姓名:毛飞  陈智骏  梁效斐  曹奇英
作者单位:东华大学计算机科学与技术学院;
基金项目:国家大学生创新性实验计划项目(101025537)
摘    要:使用CUDA平台,提出在通用图形处理器(GPGPU)上实现并行的全选主元、归一和消去等操作,加速实现并行全选主元高斯-约当消去法求解线性方程组的一种基本方法。该方法在CPU上完成解向量的恢复。根据NVIDIA公司最新Fermi架构图形处理器的特点,通过一系列的优化设计,使通用GPGPU相对Intel最新架构CPU的加速比超过了6.5倍,比Intel上一代CPU的加速比超过了10倍。

关 键 词:CUDA  并行计算  通用图形处理器  全选主元高斯-约当消去法  

RESEARCH AND COMPARISON ON PARALLEL GAUSS-JORDAN ELIMINATION ON CUDA PLATFORM
Mao Fei Chen Zhijun Liang Xiaofei Cao Qiying. RESEARCH AND COMPARISON ON PARALLEL GAUSS-JORDAN ELIMINATION ON CUDA PLATFORM[J]. Computer Applications and Software, 2011, 0(9)
Authors:Mao Fei Chen Zhijun Liang Xiaofei Cao Qiying
Affiliation:Mao Fei Chen Zhijun Liang Xiaofei Cao Qiying(School of Computer Science and Technology,Donghua University,Shanghai 201620,China)
Abstract:On CUDA platform,an elementary method is proposed to implement parallel complete pivoting,normalization,elimination and other operations on Generic Purpose Graphic Process Unit(GPGPU) in order to accelerate the implementation of parallel complete pivoting Gauss-Jordan elimination method to solve linear equations.The method recovers the resolved vector on CPU.Relying on the characteristics of NVIDIA's latest Fermi architecture GPU,after a series of optimization design,the accelerating ratio of GPGPU is 6.5 t...
Keywords:Compute unified device architecture(CUDA) Parallel computing Generic purpose graphic process unit(GPGPU) Complete pivoting Gauss-Jordan elimination method  
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号