Rubik: A Hierarchical Architecture for Efficient Graph Neural Network Training
文献类型:期刊论文
作者 | Chen, Xiaobing3,4; Wang, Yuke1; Xie, Xinfeng5; Hu, Xing3; Basak, Abanti5; Liang, Ling5; Yan, Mingyu3; Deng, Lei2; Ding, Yufei1; Du, Zidong3 |
刊名 | IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS |
出版日期 | 2022-04-01 |
卷号 | 41期号:4页码:936-949 |
ISSN号 | 0278-0070 |
关键词 | Deep learning accelerator graph neural network (GNN) |
DOI | 10.1109/TCAD.2021.3079142 |
英文摘要 | The graph convolutional network (GCN) emerges as a promising direction to learn the inductive representation in graph data commonly used in widespread applications, such as E-commerce, social networks, and knowledge graphs. However, learning from graphs is nontrivial because of its mixed computation model involving both graph analytics and neural network computing. To this end, we decompose the GCN learning into two hierarchical paradigms: 1) graph-level and 2) node-level computing. Such a hierarchical paradigm facilitates the software and hardware accelerations for GCN learning. We propose a lightweight graph reordering methodology, incorporated with a GCN accelerator architecture that equips a customized cache design to fully utilize the graph-level data reuse. We also propose a mapping methodology aware of data reuse and task-level parallelism to handle various graphs inputs effectively. The results show that Rubik accelerator design improves energy efficiency by 26.3x-1375.2x than GPU platforms across different datasets and GCN models. |
资助项目 | National Key Research and Development Program of China[2017YFA0700902] ; NSF of China[61925208] ; NSF of China[62002338] ; NSF of China[61732007] ; NSF of China[61732002] ; NSF of China[61906179] ; NSF of China[U19B2019] ; NSF of China[U20A20227] ; Beijing Natural Science Foundation[JQ18013] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32050200] ; Strategic Priority Research Program of Chinese Academy of Science[XDC05010300] ; Beijing Academy of Artificial Intelligence (BAAI) ; Beijing Nova Program of Science and Technology[Z191100001119093] ; Youth Innovation Promotion Association CAS ; Xplore Prize |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000770597100014 |
源URL | [http://119.78.100.204/handle/2XEOYT63/18938] |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Hu, Xing |
作者单位 | 1.Univ Calif Santa Barbara, Dept Comp Sci, Santa Barbara, CA 93106 USA 2.Tsinghua Univ, Dept Precis Instrument, Ctr Brain Inspired Comp Res, Beijing 10084, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100190, Peoples R China 5.Univ Calif Santa Barbara, Dept Elect & Comp Engn, Santa Barbara, CA 93106 USA |
推荐引用方式 GB/T 7714 | Chen, Xiaobing,Wang, Yuke,Xie, Xinfeng,et al. Rubik: A Hierarchical Architecture for Efficient Graph Neural Network Training[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,2022,41(4):936-949. |
APA | Chen, Xiaobing.,Wang, Yuke.,Xie, Xinfeng.,Hu, Xing.,Basak, Abanti.,...&Xie, Yuan.(2022).Rubik: A Hierarchical Architecture for Efficient Graph Neural Network Training.IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,41(4),936-949. |
MLA | Chen, Xiaobing,et al."Rubik: A Hierarchical Architecture for Efficient Graph Neural Network Training".IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 41.4(2022):936-949. |
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。