中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
An efficient scheduling algorithm for dataflow architecture using loop-pipelining

文献类型：期刊论文

作者Li, Yi1,3; Wu, Meng1; Ye, Xiaochun1,2; Li, Wenming1; Xue, Rui1,3; Wang, Da1; Zhang, Hao1; Fan, Dongrui1,3
刊名INFORMATION SCIENCES
出版日期2021-02-08
卷号547页码:1136-1153
关键词Dataflow architecture Instruction scheduling Multicast Sharing path Loop optimization
ISSN号0020-0255
DOI10.1016/j.ins.2020.09.029
英文摘要Dataflow architecture has native advantages in achieving high instruction parallelism and power efficiency for today's emerging applications such as high performance computing and deep neural network. In dataflow computing, the execution of instructions is driven by data, so the data transfer efficiency of the network on chip (NoC) is a key factor affecting performance. However, the NoC performance degrades due to the increasing use of multi-cast communications in many applications. The existing dataflow architecture instruction scheduling algorithms do not optimize multicast communication between the instruction and its successor instructions, so the routing paths of many multicast packets have forks which cause bandwidth waste and potential network congestion. We propose a sharing path awareness (SPA) algorithm to optimize multicast communication in the dataflow architecture. The algorithm shares the routing paths from the instruction to its child node to reduce the NoC bandwidth waste through the instruction scheduler. For applications using software iteration, we further extend the loop optimization to the SPA algorithm to sufficiently exploit instruction-level parallelism. Compared with the state-of-the-art algorithm, we show that the SPA algorithm achieves 20.21% average performance improvement and 15.11% energy consumption reduction for our experimental workloads. (C) 2020 Elsevier Inc. All rights reserved.
资助项目National Key Research and Development Program[2018YFB1003501] ; National Natural Science Foundation of China[61732018] ; National Natural Science Foundation of China[61872335] ; National Natural Science Foundation of China[61802367] ; National Natural Science Foundation of China[61672499] ; Austrian-Chinese Cooperative RD Project (FFG)[171111KYSB20170032] ; Austrian-Chinese Cooperative RD Project (CAS)[171111KYSB20170032] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDC05000000] ; Open Project Program of the State Key Laboratory of Mathematical Engineering and Advanced Computing[2019A07]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000590678700008
出版者ELSEVIER SCIENCE INC
源URL[http://119.78.100.204/handle/2XEOYT63/16525]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Ye, Xiaochun
作者单位1.Chinese Acad Sci, State Key Lab Comp Architecture, ICT, Beijing, Peoples R China
2.State Key Lab Math Engn & Adv Comp, Wuxi, Jiangsu, Peoples R China
3.UCAS, Sch Comp & Control Engn, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Li, Yi,Wu, Meng,Ye, Xiaochun,et al. An efficient scheduling algorithm for dataflow architecture using loop-pipelining[J]. INFORMATION SCIENCES,2021,547:1136-1153.
APA Li, Yi.,Wu, Meng.,Ye, Xiaochun.,Li, Wenming.,Xue, Rui.,...&Fan, Dongrui.(2021).An efficient scheduling algorithm for dataflow architecture using loop-pipelining.INFORMATION SCIENCES,547,1136-1153.
MLA Li, Yi,et al."An efficient scheduling algorithm for dataflow architecture using loop-pipelining".INFORMATION SCIENCES 547(2021):1136-1153.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。