A Resource Efficient CNN Accelerator for Sensor Signal Processing Based on FPGA

被引:0
|
作者
Wu, Ruidong [1 ]
Liu, Bing [1 ]
Fu, Ping [1 ]
Chen, Haolin [1 ]
机构
[1] Harbin Inst Technol, Sch Elect & Informat Engn, Harbin 150001, Heilongjiang, Peoples R China
基金
中国国家自然科学基金;
关键词
CNN; FPGA; efficient accelerator; sensor signal processing; SVM;
D O I
10.1142/S0218126623500755
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
With the use of Convolutional Neural Network (CNN) in the application of sensor signal processing system, it usually faces the urgent requirements of system integration, high throughput, hardware resource and energy efficiency. This paper introduces a resource efficient accelerator with general two-dimensional multiply-add array operator to focus on the characteristic of sensor signal processing, which can be applied to standard CNN, depth-wise CNN, Fully Connected (FC) layer for varied networks. Meanwhile, resource estimation model is also constructed to provide the exploration of parallel parameters for computing efficiency. Finally, a board-level verification is implemented to demonstrate the efficiency of proposed accelerator with common scene of LeNet and complex scene of MobileNetV1. Experimental results show that the Inferences Per Second (IPS) of 332225 and 1498 is realized with 100MHz frequency. The corresponding efficiency is 88.84% and 61.09%, which outperforms other related works about CNN accelerator design in terms of signal processing. This paper is also applicable and scalable to other fields about effective acceleration research.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Efficient CNN Accelerator on FPGA
    Kala, S.
    Nalesh, S.
    IETE JOURNAL OF RESEARCH, 2020, 66 (06) : 733 - 740
  • [2] FitNN: A Low-Resource FPGA-Based CNN Accelerator for Drones
    Zhang, Zhichao
    Mahmud, M. A. Parvez
    Kouzani, Abbas Z.
    IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (21) : 21357 - 21369
  • [3] An Efficient CNN Architecture for Image Classification on FPGA Accelerator
    Mujawar, Shahmustafa
    Kiran, Divya
    Ramasangu, Hariharan
    2018 SECOND INTERNATIONAL CONFERENCE ON ADVANCES IN ELECTRONICS, COMPUTERS AND COMMUNICATIONS (ICAECC), 2018,
  • [4] Resource-Efficient Optimization for FPGA-Based Convolution Accelerator
    Ma, Yanhua
    Xu, Qican
    Song, Zerui
    ELECTRONICS, 2023, 12 (20)
  • [5] Automatic Compiler Based FPGA Accelerator for CNN Training
    Venkataramanaiah, Shreyas Kolala
    Ma, Yufei
    Yin, Shihui
    Nurvithadhi, Eriko
    Dasu, Aravind
    Cao, Yu
    Seo, Jae-sun
    2019 29TH INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE LOGIC AND APPLICATIONS (FPL), 2019, : 166 - 172
  • [6] High Throughput CNN Accelerator Design Based on FPGA
    Xie, Liang
    Fan, Xitian
    Cao, Wei
    Wang, Lingli
    2018 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (FPT 2018), 2018, : 277 - 280
  • [7] A Resource Efficient Integer-Arithmetic-Only FPGA-Based CNN Accelerator for Real-Time Facial Emotion Recognition
    Kim, Jaemyung
    Kang, Jin-Ku
    Kim, Yongwoo
    IEEE ACCESS, 2021, 9 : 104367 - 104381
  • [8] AN ACCELERATOR OF EFFICIENT DSP BASED ON FPGA
    Zhang Boyu
    Zou Ha
    Tang Ming
    Lin Qiutong
    2022 19TH INTERNATIONAL COMPUTER CONFERENCE ON WAVELET ACTIVE MEDIA TECHNOLOGY AND INFORMATION PROCESSING (ICCWAMTIP), 2022,
  • [9] An Efficient FPGA Accelerator Optimized for High Throughput Sparse CNN Inference
    Wen, Jiayu
    Ma, Yufei
    Wang, Zhongfeng
    APCCAS 2020: PROCEEDINGS OF THE 2020 IEEE ASIA PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS (APCCAS 2020), 2020, : 165 - 168
  • [10] Efficient Dynamic Reconfigurable CNN Accelerator for Edge Intelligence Computing on FPGA
    Shi, Kaisheng
    Wang, Mingwei
    Tan, Xin
    Li, Qianghua
    Lei, Tao
    INFORMATION, 2023, 14 (03)