首页 | 本学科首页   官方微博 | 高级检索  
     

基于延迟隐藏因子的GPU 计算模型
引用本文:袁良,张云泉,龙国平,王可,张先轶. 基于延迟隐藏因子的GPU 计算模型[J]. 软件学报, 2010, 21(Z1): 251-262
作者姓名:袁良  张云泉  龙国平  王可  张先轶
作者单位:中国科学院 软件研究所 并行软件与计算科学实验室,北京 100190; 中国科学院 计算机科学国家重点实验室,北京 100190; 中国科学院 研究生院,北京 100049;中国科学院 软件研究所 并行软件与计算科学实验室,北京 100190; 中国科学院 计算机科学国家重点实验室,北京 100190;中国科学院 软件研究所 并行软件与计算科学实验室,北京 100190;中国科学院 软件研究所 并行软件与计算科学实验室,北京 100190;中国科学院 软件研究所 并行软件与计算科学实验室,北京 100190; 中国科学院 计算机科学国家重点实验室,北京 100190
基金项目:Supported by the National High-Tech Research and Development Plan of China under Grant Nos.2006AA01A125, 2009AA01A129, 2009AA01A134 (国家高技术研究发展计划(863)); 核高基资助项目(2009ZX01036-001-002); 中国科学院知识创新工程重大项目课题(KGCX1-YW-13); 财政部国家重大科研装备研制项目(ZDYZ2008-2)
摘    要:近年来在生物计算,科学计算等领域成功地应用了GPU 加速计算并获得了较高加速比.然而在GPU 上编程和调优过程非常繁琐,为此,研究人员提出了许多提高编程效率的编程模型和编译器,以及指导程序优化的计算模型,在一定程度上简化了GPU上的算法设计和优化,但是已有工作都存在一些不足.针对GPU低延迟高带宽的特性,提出了基于延迟隐藏因子的GPU 计算模型,模型提取算法隐藏延迟的能力,以指导算法优化.利用3 种矩阵乘算法进行实测与模型预测,实验结果表明,在简化模型的情况下,平均误差率为0.19.

关 键 词:GPU 通用计算  计算模型  性能模型  延迟隐藏因子  GPU 性能优化
收稿时间:2010-06-15
修稿时间:2010-12-10

A GPU Computational Model Based on Latency Hidden Factor
YUAN Liang,ZHANG Yun-Quan,LONG Guo-Ping,WANG Ke and ZHANG Xian-Yi. A GPU Computational Model Based on Latency Hidden Factor[J]. Journal of Software, 2010, 21(Z1): 251-262
Authors:YUAN Liang  ZHANG Yun-Quan  LONG Guo-Ping  WANG Ke  ZHANG Xian-Yi
Affiliation:Laboratory of Parallel Software and Computational Science, Institute of Software, The Chinese Academy of Sciences, Beijing 100190, China; State Key Laboratory of Computer Science, Institute of Software, The Chinese Academy of Sciences, Beijing 100190, Chi;Laboratory of Parallel Software and Computational Science, Institute of Software, The Chinese Academy of Sciences, Beijing 100190, China; State Key Laboratory of Computer Science, Institute of Software, The Chinese Academy of Sciences, Beijing 100190, Chi;Laboratory of Parallel Software and Computational Science, Institute of Software, The Chinese Academy of Sciences, Beijing 100190, China;Laboratory of Parallel Software and Computational Science, Institute of Software, The Chinese Academy of Sciences, Beijing 100190, China;Laboratory of Parallel Software and Computational Science, Institute of Software, The Chinese Academy of Sciences, Beijing 100190, China; State Key Laboratory of Computer Science, Institute of Software, The Chinese Academy of Sciences, Beijing 100190, Chi
Abstract:The general purpose GPU computing technology has been successfully used to accelerator many important applications. Though researches have designed many programming models and performance models, the amount of effort required to optimize the performance of applications on GPUs is still very high. In this paper, we propose a GPU computational model based on the ability that how much an algorithm could hide the latency. The experimental results show that our model could predict three matrix multiplication algorithms well.
Keywords:general purpose GPU computing   computational model   performance model   latency hidden factor   GPU optimization
点击此处可从《软件学报》浏览原始摘要信息
点击此处可从《软件学报》下载全文
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