An efficient dataflow accelerator for scientific applications

doi:10.1016/j.future.2020.03.023

	An efficient dataflow accelerator for scientific applications
	Ye, Xiaochun 1; Tan, Xu 1,2; Wu, Meng 1; Feng, Yujing 1,2; Wang, Da 1; Zhang, Hao 1; Pei, Songwen 1,3; Fan, Dongrui 1,2
	2020-11-01
发表期刊	FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
ISSN	0167-739X
卷号	112 页码:580-588
摘要	Dataflow architecture has been proved to be promising in high-performance computing. Traditional dataflow architectures are not efficient enough in typical scientific applications such as stencil and FFT due to low utilization of function units. Based on the blocking and parallelism features of scientific applications, we design SPU, an efficient dataflow architecture for scientific applications. In SPU, dataflow graphs translated from the loop body in scientific applications are mapped to the Processing Element(PE) Array. Iterations enter the dataflow graph in pipeline during execution meanwhile three levels of parallelism are exploited to improve the utilization of function units in dataflow architectures: inner-graph parallelism, pipelining parallelism and inter graph parallelism. The experimental results show that the average energy efficiency of SPU achieves 25.97GFlops/W in 40 nm technology and the utilization of floating point function units in SPU is 2.82x that of typical dataflow architecture on average for typical scientific applications. (C) 2020 Elsevier B.V. All rights reserved.
关键词	Dataflow architecture Scientific computing Instruction level parallelism
DOI	10.1016/j.future.2020.03.023
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan of China[2018YFB1003501] ; National Natural Science Foundation of China[61732018] ; National Natural Science Foundation of China[61872335] ; National Natural Science Foundation of China[61802367] ; International Partnership Program of Chinese Academy of Sciences[171111KYSB20170032] ; Innovation Project of the State Key Laboratory of Computer Architecture, ICT, CAS, China[CARCH3303] ; Innovation Project of the State Key Laboratory of Computer Architecture, ICT, CAS, China[CARCH3407] ; Innovation Project of the State Key Laboratory of Computer Architecture, ICT, CAS, China[CARCH3502] ; Innovation Project of the State Key Laboratory of Computer Architecture, ICT, CAS, China[CARCH3505] ; State Key Laboratory of Computer Architecture, ICT, CAS, China[CARCH201807]
WOS研究方向	Computer Science
WOS类目	Computer Science, Theory & Methods
WOS记录号	WOS:000567825900006
出版者	ELSEVIER
引用统计	被引频次：5[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/2XEOYT63/15518
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Fan, Dongrui
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 3.Univ Shanghai Sci & Technol, Sch Opt Elect & Comp Engn, Shanghai 200093, Peoples R China
推荐引用方式 GB/T 7714	Ye, Xiaochun,Tan, Xu,Wu, Meng,et al. An efficient dataflow accelerator for scientific applications[J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE,2020,112:580-588.
APA	Ye, Xiaochun.,Tan, Xu.,Wu, Meng.,Feng, Yujing.,Wang, Da.,...&Fan, Dongrui.(2020).An efficient dataflow accelerator for scientific applications.FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE,112,580-588.
MLA	Ye, Xiaochun,et al."An efficient dataflow accelerator for scientific applications".FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 112(2020):580-588.