跳到主要导航 跳到搜索 跳到主要内容

A Computing Efficient Hardware Architecture for Sparse Deep Neural Network Computing

  • Beihang University
  • Tsinghua University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Convolutional Neural Networks (CNNs) have demonstrated significant performance in AI (artificial intelligence) systems. However, CNNs often have tens or even hundreds of neural layers with millions of parameters to achieve state-of-the-art performance, which hinders the deployment to some resource limited scenarios. Meanwhile, those parameters and data usually are sparse, which results in useless calculation as well as unbalanced calculation. To solve these problem, we propose a computing efficient hardware architecture. In order to decrease calculating redundancy, we filter zero-valued weights and zero-valued feature maps. To reduce redundant memory consumption, we propose a memory division and a data reuse mechanism. To resolve load imbalance, we implement a near-zero-cost scheduling switching strategy. Experimental results show that our architecture saves, on average, 22.6% memory times and 60.5% computing time over the state-of-the-art NN accelerator.

源语言英语
主期刊名2018 14th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2018 - Proceedings
编辑Ting-Ao Tang, Fan Ye, Yu-Long Jiang
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781538644409
DOI
出版状态已出版 - 5 12月 2018
活动14th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2018 - Qingdao, 中国
期限: 31 10月 20183 11月 2018

出版系列

姓名2018 14th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2018 - Proceedings

会议

会议14th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2018
国家/地区中国
Qingdao
时期31/10/183/11/18

指纹

探究 'A Computing Efficient Hardware Architecture for Sparse Deep Neural Network Computing' 的科研主题。它们共同构成独一无二的指纹。

引用此