Understanding Big Data Analytics Workloads on Modern Processors

doi:10.1109/TPDS.2016.2625244

	Understanding Big Data Analytics Workloads on Modern Processors
	Jia, Zhen 1,2; Zhan, Jianfeng 1,2; Wang, Lei 1,2; Luo, Chunjie 1,2; Gao, Wanling 1,2; Jin, Yi 3; Han, Rui 1,2; Zhang, Lixin 1,2
	2017-06-01
发表期刊	IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
ISSN	1045-9219
卷号	28 期号:6 页码:1797-1810
摘要	Big data analytics workloads are very significant ones in modern data centers, and it is more and more important to characterize their representative workloads and understand their behaviors so as to improve the performance of data center computer systems. In this paper, we embark on a comprehensive study to understand the impacts and performance implications of the big data analytics workloads on the systems equipped with modern superscalar out-of-order processors. After investigating three most important application domains in Internet services in terms of page views and daily visitors, we choose 11 representative data analytics workloads and characterize their micro-architectural behaviors by using hardware performance counters. Our study reveals that the big data analytics workloads share many inherent characteristics, which place them in a different class from the traditional workloads and the scale-out services. To further understand the characteristics of big data analytics workloads, we perform correlation analysis to identify the most key factors that affect cycles per instruction (CPI). Also, we reveal that the increasing complexity of the big data software stacks will put higher pressures on the modern processor pipelines.
关键词	Big data analytics workload characterization micro-architectural characteristics performance optimization
DOI	10.1109/TPDS.2016.2625244
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2016YFB1000600] ; National Key Research and Development Program of China[2016YFB1000601]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000401365300020
出版者	IEEE COMPUTER SOC
引用统计	被引频次：16[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/7170
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Jia, Zhen
作者单位	1.Chinese Acad Sci, ICT, State Key Lab Comp Architecture, Beijing 100049, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Beijing Acad Sci & Technol, Beijing Comp Ctr, Beijing 100089, Peoples R China
推荐引用方式 GB/T 7714	Jia, Zhen,Zhan, Jianfeng,Wang, Lei,et al. Understanding Big Data Analytics Workloads on Modern Processors[J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS,2017,28(6):1797-1810.
APA	Jia, Zhen.,Zhan, Jianfeng.,Wang, Lei.,Luo, Chunjie.,Gao, Wanling.,...&Zhang, Lixin.(2017).Understanding Big Data Analytics Workloads on Modern Processors.IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS,28(6),1797-1810.
MLA	Jia, Zhen,et al."Understanding Big Data Analytics Workloads on Modern Processors".IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 28.6(2017):1797-1810.