Neural Network Accelerator Comparison

For use in publications and presentations please cite this data collection as follows:
K. Guo, W. Li, K. Zhong, Z. Zhu, S. Zeng, T. Xie, S. Han, Y. Xie, P. Debacker, M. Verhelst, Y. Wang. "Neural Network Accelerator Comparison" [Online]. Available: https://nicsefc.ee.tsinghua.edu.cn/projects/neural-network-accelerator/
Introduction video (Chinese): https://www.bilibili.com/video/BV1ct4y1X7tj?share_source=copy_web
[Update] For LLM (large language model) accelerator comparison, please refer to https://dai.sjtu.edu.cn/project.html

    Select all
    Simulation
    Test
    Product
    Select all
    Academia
    Industry
    Select all
    FPGA
    ASIC (Digital)
    GPU
    ASIC (Mixed)
    CPU
    Select all
    2010
    2011
    2014
    2015
    2016
    2017
    2018
    2019
    2020
    2021
    2022
    2023
    2024
    Select all
    CNN
    RNN
    CNN+RNN
    3D CNN
    LLM
    Diffusion
    others
    Select all
    peak performance
    real performance
    Select all
    YES
    NO
    Select all
    FP32
    FP16
    FP8
    INT16
    INT12
    INT8
    INT6
    INT4
    INT2
    Ternary
    Binary
    others
    Select all
    FP32
    FP16
    FP8
    INT16
    INT12
    INT8
    INT6
    INT4
    INT2
    Ternary
    Binary
    others
    Select all
    No
    A
    W
    A+W
    At
    Wt
    At+Wt

Copy
Close
* Peak performance calculated by TDP while real performance calculated by the measured power.
Title
Author
Affiliation
Fabric
Energy Efficiency
Benchmark
Support NN Type
Sparsity
Precision
Publisher
Year
URL

Submit your results or have any problems: nics-efc@tsinghua.edu.cn
Authored by: Kaiyuan Guo, Wenshuo Li, Kai Zhong, Zhenhua Zhu, Shulin Zeng, Tongxin Xie, Song Han, Yuan Xie, Peter Debacker, Marian Verhelst, Yu Wang
Acknowledgement: Yuzhi Wang, Lixue Xia, Xuefei Ning, and those who gave precious suggestions to this page.