Towards a Uniform Template-based Architecture for Accelerating 2D and 3D CNNs on FPGA

@inproceedings{Shen2018TowardsAU,
  title={Towards a Uniform Template-based Architecture for Accelerating 2D and 3D CNNs on FPGA},
  author={Junzhong Shen and You Huang and Zelong Wang and Yuran Qiao and Mei Wen and Chunyuan Zhang},
  booktitle={FPGA '18},
  year={2018}
}
  • Junzhong Shen, You Huang, +3 authors Chunyuan Zhang
  • Published in FPGA '18 2018
  • Computer Science
  • Highlight Information
    Three-dimensional convolutional neural networks (3D CNNs) are used efficiently in many computer vision applications. [...] Key Method Furthermore, we also develop a uniform analytical model to facilitate efficient design space explorations of 2D and 3D CNN accelerators based on our architecture. Finally, we demonstrate the effectiveness of the template-based architecture by implementing accelerators for real-life 2D and 3D CNNs (VGG16 and C3D) on multiple FPGA platforms. On S2C VUS440, we achieve up to 1.13…Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 28 CITATIONS

    Scale-out Acceleration for 3D CNN-based Lung Nodule Segmentation on a Multi-FPGA System

    VIEW 10 EXCERPTS
    CITES METHODS & BACKGROUND

    3D-based Video Recognition Acceleration by Leveraging Temporal Locality

    VIEW 4 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Systolic Cube: A Spatial 3D CNN Accelerator Architecture for Low Power Video Analysis

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Hardware Compilation of Deep Neural Networks: An Overview

    • Ruizhe Zhao, Shuanglong Liu, +8 authors Wayne Luk
    • Computer Science
    • 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)
    • 2018
    VIEW 9 EXCERPTS
    HIGHLY INFLUENCED

    Stride 2 1-D, 2-D, and 3-D Winograd for Convolutional Neural Networks

    VIEW 1 EXCERPT
    CITES METHODS

    Accelerating HotSpots in Deep Neural Networks on a CAPI-Based FPGA

    • Md. Syadus Sefat, Semih Aslan, Jeffrey W. Kellington, Apan Qasem
    • Computer Science
    • 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)
    • 2019
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Automatic Generation of Multi-Precision Multi-Arithmetic CNN Accelerators for FPGAs

    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-7 OF 7 REFERENCES

    Caffeine: Towards uniformed representation and acceleration for deep convolutional neural networks

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Going Deeper with Embedded FPGA Platform for Convolutional Neural Network

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL