| 基于指导语句的CUDA程序性能分析工具研究与实现 |
| |
| 引用本文： | 李建江,路川,张磊.基于指导语句的CUDA程序性能分析工具研究与实现[J].电子科技大学学报（自然科学版）,2012,41(2):280-284. |
| |
| 作者姓名： | 李建江 路川 张磊 |
| |
| 作者单位： | 1.北京科技大学计算机科学与技术系 北京 海淀区 100083 |
| |
| 基金项目： | 教育部科学技术研究重点项目(108008);北京市教委重点学科(XK100080537) |
| |
| 摘 要： | 近年来,GPU的快速发展与NVIDIA公司推出的CUDA技术,推动着GPU在高性能计算领域中的应用。研究并实现CUDA程序性能分析工具,对充分利用GPU的计算优势和提高CUDA架构下并行程序的执行性能具有重要的意义。该文分析了GPU硬件平台的特点和CUDA并行编程模型,结合CPU集群环境下并行程序的性能分析,设计并实现了一种基于指导语句的CUDA程序性能分析工具,并实验验证了其在不同GPU硬件平台上的有效性。
|
| 关 键 词： | CUDA 指导语句 高性能计算 性能分析 程序优化 |
| 收稿时间： | 2010-07-26 |
Research and Implementation of Performance Analysis Tool for CUDA Programs with Directive |
| |
| LI Jian-jiang,LU Chuan,ZHANG Lei.Research and Implementation of Performance Analysis Tool for CUDA Programs with Directive[J].Journal of University of Electronic Science and Technology of China,2012,41(2):280-284. |
| |
| Authors: | LI Jian-jiang LU Chuan ZHANG Lei |
| |
| Affiliation: | 1.Department of computer science and technology,University of science and technology Beijing Haidian Beijing 100083 |
| |
| Abstract: | In recent years, the rapid expansion of graphics processing unit (GPU) as well as the computer unified device architecture (CUDA) technology proposed by NVIDIA pushes forward the application of GPU in the field of high performance computing (HPC). In this paper, GPU's architecture and CUDA programming model are introduced first. According to the method of parallel program performance analysis in CPU cluster mode, a performance analysis tool for CUDA programs based on directive is designed and implemented. Experiment results validate the validity of this performance analysis tool on different GPU hardware platforms. |
| |
| Keywords: | |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《电子科技大学学报（自然科学版）》浏览原始摘要信息 |
|
点击此处可从《电子科技大学学报（自然科学版）》下载全文 |
