Spatial Data Dependence Graph Simulator for Convolutional Neural Network Accelerators

被引：0
|
作者：
Wang, Jooho [1 ]
Kim, Jiwon [1 ]
Moon, Sungmin [1 ]
Kim, Sunwoo [1 ]
Park, Sungkyung [2 ]
Park, Chester Sungchung [1 ]
机构：
[1] Konkuk Univ, Dept Elect Engn, Seoul, South Korea
[2] Pusan Natl Univ, Dept Elect Engn, Busan, South Korea
来源：
2019 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS 2019) | 2019年
关键词：
convolution neural network (CNN); accelerator; dataflow; data dependence graph;
D O I：
10.1109/aicas.2019.8771561
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A spatial data dependence graph (S-DDG) is newly proposed to model an accelerator dataflow. The pre-RTL simulator based on the S-DDG helps to explore the design space in the early design phase. The simulation results show the impact of memory latency and bandwidth on a convolutional neural network (CNN) accelerator.
引用
收藏
页码：309 / 310
页数：2
相关论文
共 50 条
  • [1] Spatial Data Dependence Graph Based Pre-RTL Simulator for Convolutional Neural Network Dataflows
    Wang, Jooho
    Park, Sungkyung
    Park, Chester Sungchung
    IEEE ACCESS, 2022, 10 : 11382 - 11403
  • [2] Convolutional Neural Network Outperforms Graph Neural Network on the Spatially Variant Graph Data
    Boronina, Anna
    Maksimenko, Vladimir
    Hramov, Alexander E. E.
    MATHEMATICS, 2023, 11 (11)
  • [3] GShuttle: Optimizing Memory Access Efficiency for Graph Convolutional Neural Network Accelerators
    Li, Jia-Jun
    Wang, Ke
    Zheng, Hao
    Louri, Ahmed
    JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2023, 38 (01) : 115 - 127
  • [4] GShuttle: Optimizing Memory Access Efficiency for Graph Convolutional Neural Network Accelerators
    Jia-Jun Li
    Ke Wang
    Hao Zheng
    Ahmed Louri
    Journal of Computer Science and Technology, 2023, 38 : 115 - 127
  • [5] A graph convolutional neural network for classification of building patterns using spatial vector data
    Yan, Xiongfeng
    Ai, Tinghua
    Yang, Min
    Yin, Hongmei
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2019, 150 : 259 - 273
  • [6] NNSim: A Past and Accurate SystemC/TLM Simulator for Deep Convolutional Neural Network Accelerators
    Lee, Yi-Che
    Hsu, Ting-Shuo
    Chen, Chun-Tse
    Liou, Jing-Jia
    Lu, Juin-Ming
    2019 INTERNATIONAL SYMPOSIUM ON VLSI DESIGN, AUTOMATION AND TEST (VLSI-DAT), 2019,
  • [7] LISA: Graph Neural Network based Portable Mapping on Spatial Accelerators
    Li, Zhaoying
    Wu, Dan
    Wijerathne, Dhananjaya
    Mitra, Tulika
    2022 IEEE INTERNATIONAL SYMPOSIUM ON HIGH-PERFORMANCE COMPUTER ARCHITECTURE (HPCA 2022), 2022, : 444 - 459
  • [8] Mining the Graph Representation of Traffic Speed Data for Graph Convolutional Neural Network
    Mao, Jiannan
    Huang, Hao
    Chen, Yuting
    Lu, Weike
    Chen, Guoqiang
    Liu, Lan
    2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2021, : 1205 - 1210
  • [9] Gesture recognition of graph convolutional neural network based on spatial domain
    Chen, Hong
    Zhao, Hongdong
    Qi, Baoqiang
    Zhang, Shuai
    Yu, Zhanghong
    NEURAL COMPUTING & APPLICATIONS, 2023, 35 (03): : 2157 - 2167
  • [10] Gesture recognition of graph convolutional neural network based on spatial domain
    Hong Chen
    Hongdong Zhao
    Baoqiang Qi
    Shuai Zhang
    Zhanghong Yu
    Neural Computing and Applications, 2023, 35 : 2157 - 2167
12345