Chinese Journal of Liquid Crystals and Displays, Volume. 40, Issue 3, 448(2025)

Design of heterogeneous FPGA hardware accelerator based on CNN

Haolin JI1,2,3, Wei XU1,3、*, Yongjie PIAO1,3, Xiaobin WU1,2,3, and Tan GAO1,2,3
Author Affiliations
  • 1Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China
  • 2University of Chinese Academy of Sciences, Beijing 100049, China
  • 3Key Laboratory of Space-Based Dynamic & Rapid Optical Imaging Technology, Chinese Academy of Sciences, Changchun 130033,China
  • show less

    Due to limitations in hardware platform computing power and storage resources, achieving energy-efficient and efficient convolutional neural networks (CNNs) by using embedded systems remains a primary challenge for hardware designers. In this context, a complete design of a heterogeneous embedded system implemented by using a system-on-chip (SoC) with a field-programmable gate array (FPGA) is proposed. This design adopts a cascaded input multiplexing structure, enabling two independent multiply-accumulate operations in a single DSP, reducing external memory access, enhancing system efficiency, and lowering power consumption. Compared to other designs, the power efficiency is improved by over 38.7%. The design framework is successfully deployed in a large-scale CNN network on low-cost devices, significantly improving power efficiency of the network model. The power efficiency achieved on the ZYNQ XC7Z045 device can even reach 102 Gops/W. Furthermore, when inferring the VGG-16’s CONV layers by using this framework, a frame rate of up to 10.9 fps is achieved, which demonstrates the framework’?s effective acceleration of CNN inference in power-constrained environments.

    Keywords
    Tools

    Get Citation

    Copy Citation Text

    Haolin JI, Wei XU, Yongjie PIAO, Xiaobin WU, Tan GAO. Design of heterogeneous FPGA hardware accelerator based on CNN[J]. Chinese Journal of Liquid Crystals and Displays, 2025, 40(3): 448

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Circuit Design

    Received: Jul. 12, 2024

    Accepted: --

    Published Online: Apr. 27, 2025

    The Author Email: Wei XU (xwciomp@163.com)

    DOI:10.37188/CJLCD.2024-0198

    Topics