General Reuse-Centric CNN Accelerator

被引:6
|
作者
Cicek, Nihat Mert [1 ,2 ]
Ning, Lin [3 ]
Ozturk, Ozcan [4 ]
Shen, Xipeng [3 ]
机构
[1] Aselsan Inc, TR-06200 Yenimahalle Ankara, Turkey
[2] Bilkent Univ, Dept Comp Engn, TR-06800 Ankara, Turkey
[3] North Carolina State Univ, Dept Comp Sci, Raleigh, NC 27695 USA
[4] Bilkent Univ, Dept Comp Engn, TR-06800 Ankara, Turkey
基金
美国国家科学基金会;
关键词
Neurons; Hardware; Convolution; Engines; Software; Acceleration; IEEE Senior Members; CNN; reuse-centric; accelerator;
D O I
10.1109/TC.2021.3064608
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This article introduces the first general reuse-centric accelerator for CNN inferences. Unlike prior work that exploits similarities only across consecutive video frames, general reuse-centric accelerator is able to discover similarities among arbitrary patches within an image or across independent images, and translate them into computation time and energy savings. Experiments show that the accelerator complements both prior software-based CNN and various CNN hardware accelerators, producing up to 14.96X speedups for similarity discovery, up to 2.70X speedups for overall inference.
引用
收藏
页码:880 / 891
页数:12
相关论文
共 50 条
  • [21] Model Parallelism Optimization for CNN FPGA Accelerator
    Wang, Jinnan
    Tong, Weiqin
    Zhi, Xiaoli
    ALGORITHMS, 2023, 16 (02)
  • [22] An end-to-end RNS CNN Accelerator
    Sakellariou, Vasilis
    Paliouras, Vassilis
    Kouretas, Ioannis
    Saleh, Hani
    Stouraitis, Thanos
    2024 IEEE 6TH INTERNATIONAL CONFERENCE ON AI CIRCUITS AND SYSTEMS, AICAS 2024, 2024, : 75 - 79
  • [23] An Area Efficient Superconducting Unary CNN Accelerator
    Gonzalez-Guerrero, Patricia
    Huch, Kylie
    Patra, Nirmalendu
    Popovici, Thom
    Michelogiannakis, George
    2023 24TH INTERNATIONAL SYMPOSIUM ON QUALITY ELECTRONIC DESIGN, ISQED, 2023, : 675 - 682
  • [24] Towards Reconfigurable CNN Accelerator for FPGA Implementation
    Syed, Rizwan Tariq
    Andjelkovic, Marko
    Ulbricht, Markus
    Krstic, Milos
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2023, 70 (03) : 1249 - 1253
  • [25] DIMA: A Depthwise CNN In-Memory Accelerator
    Angizi, Shaahin
    He, Zhezhi
    Fan, Deliang
    2018 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN (ICCAD) DIGEST OF TECHNICAL PAPERS, 2018,
  • [26] FiBHA: Fixed Budget Hybrid CNN Accelerator
    Qararyah, Fareed
    Azhar, Muhammad Waqar
    Trancoso, Pedro
    2022 IEEE 34TH INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING (SBAC-PAD 2022), 2022, : 180 - 190
  • [27] Moving CNN Accelerator Computations Closer to Data
    Gudaparthi, Sumanth
    Narayanan, Surya
    Balasubramonian, Rajeev
    2018 1ST WORKSHOP ON ENERGY EFFICIENT MACHINE LEARNING AND COGNITIVE COMPUTING FOR EMBEDDED APPLICATIONS (EMC2), 2018, : 34 - 38
  • [28] INCAME: Interruptible CNN Accelerator for Multirobot Exploration
    Yu, Jincheng
    Xu, Zhilin
    Zeng, Shulin
    Yu, Chao
    Qiu, Jiantao
    Shen, Chaoyang
    Xu, Yuanfan
    Dai, Guohao
    Wang, Yu
    Yang, Huazhong
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2022, 41 (04) : 964 - 978
  • [29] Data Optimization CNN Accelerator Design on FPGA
    Hu, Wei
    Chen, Shuang
    Li, Zhenhao
    Liu, Tianyi
    Li, Yining
    2019 IEEE INTL CONF ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, BIG DATA & CLOUD COMPUTING, SUSTAINABLE COMPUTING & COMMUNICATIONS, SOCIAL COMPUTING & NETWORKING (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2019), 2019, : 294 - 299
  • [30] Optimizing CNN Accelerator With Improved Roofline Model
    Fang, Shaoxia
    Zeng, Shulin
    Wang, Yu
    2020 IEEE 33RD INTERNATIONAL SYSTEM-ON-CHIP CONFERENCE (SOCC), 2020, : 90 - 95