首站-论文投稿智能助手
典型文献
Toward High-Performance Delta-Based Iterative Processing with a Group-Based Approach
文献摘要:
Many systems have been built to employ the delta-based iterative execution model to support iterative algo-rithms on distributed platforms by exploiting the sparse computational dependencies between data items of these iterative algorithms in a synchronous or asynchronous approach.However,for large-scale iterative algorithms,existing synchronous solutions suffer from slow convergence speed and load imbalance,because of the strict barrier between iterations;while existing asynchronous approaches induce excessive redundant communication and computation cost as a result of being barrier-free.In view of the performance trade-off between these two approaches,this paper designs an efficient execution manager,called Aiter-R,which can be integrated into existing delta-based iterative processing systems to efficiently support the execution of delta-based iterative algorithms,by using our proposed group-based iterative execution approach.It can efficiently and correctly explore the middle ground of the two extremes.A heuristic scheduling algorithm is further proposed to allow an iterative algorithm to adaptively choose its trade-off point so as to achieve the maximum efficiency.Experimen-tal results show that Aiter-R strikes a good balance between the synchronous and asynchronous policies and outperforms state-of-the-art solutions.It reduces the execution time by up to 54.1%and 84.6%in comparison with existing asynchronous and the synchronous models,respectively.
文献关键词:
作者姓名:
Hui Yu;Xin-Yu Jiang;Jin Zhao;Hao Qi;Yu Zhang;Xiao-Fei Lia;Hai-Kun Liu;Fu-Bing Mao;Hai Jin
作者机构:
National Engineering Research Center for Big Data Technology and System,Huazhong University of Science and Technology,Wuhan 430074,China;Service Computing Technology and System Laboratory,Huazhong University of Science and Technology Wuhan 430074,China;Cluster and Grid Computing Laboratory,Huazhong University of Science and Technology,Wuhan 430074,China;School of Computer Science and Technology,Huazhong University of Science and Technology,Wuhan 430074,China;School of Computer Science and Technology,HUST,Wuhan;School of Computer Science and Technology at HUST,Wuhan;School of Computer Science and Technology,Huazhong University of Science and Technology,Wuhan;Huazhong University of Science and Technology(HUST),Wuhan
引用格式:
[1]Hui Yu;Xin-Yu Jiang;Jin Zhao;Hao Qi;Yu Zhang;Xiao-Fei Lia;Hai-Kun Liu;Fu-Bing Mao;Hai Jin-.Toward High-Performance Delta-Based Iterative Processing with a Group-Based Approach)[J].计算机科学技术学报(英文版),2022(04):797-813
A类:
Aiter,Experimen
B类:
Toward,High,Performance,Delta,Based,Iterative,Processing,Group,Approach,Many,systems,have,been,built,employ,delta,iterative,execution,support,distributed,platforms,by,exploiting,sparse,computational,dependencies,between,data,items,these,algorithms,asynchronous,However,large,scale,existing,solutions,suffer,from,slow,convergence,speed,load,imbalance,because,strict,barrier,iterations,while,approaches,induce,excessive,redundant,communication,cost,being,free,In,view,performance,trade,off,two,this,paper,designs,manager,called,which,can,integrated,into,processing,efficiently,using,our,proposed,group,correctly,explore,middle,ground,extremes,heuristic,scheduling,further,allow,adaptively,choose,its,point,achieve,maximum,efficiency,tal,results,show,that,strikes,good,policies,outperforms,state,art,reduces,comparison,models,respectively
AB值:
0.544796
相似文献
A Distributed Framework for Large-scale Protein-protein Interaction Data Analysis and Prediction Using MapReduce
Lun Hu-School of Computer Science and Technology, Dongguan University of Technology, Dongguan 523808,China;Xinjiang Technical Institute of Physics and Chemistry,Chinese Academy of Sciences, Urumqi 830000, China;School of Computer Science and Technology,Wuhan University of Technology, Wuhan 430070, China;Chongqing Engineering Research Center of Big Data Application for Smart Cities, and Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing 400714, China;Center of Research Excellence in Renewable Energy and Power Systems, and the Department of Electrical and Computer Engineering, Faculty of Engineering, King Abdulaziz University, Jeddah 21589, Saudi Arabia;Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ 07102 USA
机标中图分类号,由域田数据科技根据网络公开资料自动分析生成,仅供学习研究参考。