Increasing PE Utilization with a SW/HW Co-Design Technique for Sparse Convolutional Neural Networks

Wei Fan Tseng, Bo Cheng Lai, Jyun Wei Pan

研究成果: Conference contribution同行評審

摘要

Pruning convolution neural networks (CNN) has proved to be an effective technique to decrease the network size without loss of accuracy. By processing the compressed format of the network, the energy consumption can be considerably reduced. However, the existing SIMD-like sparse CNN accelerator suffers from low processing engine (PE) utilization due to the irregular distribution of effectual pairs. In this paper, we address this issue by proposing a software and hardware codesign technique, including a novel data compression scheme and a dedicated module to handle this compressed format. When compared to a state-of-the-art SIMD-like accelerator, the proposed co-design technique can reduce the computation time of conv3, conv4, conv5 of AlexNet by 15%, 33%, 31%.

原文English
主出版物標題Proceedings of the 2019 8th International Conference on Innovation, Communication and Engineering, ICICE 2019
編輯Shoou-Jinn Chang, Sheng-Joue Young, Artde Donald Kin-Tak Lam, Liang-Wen Ji, Hao-Ying Lu, Stephen D. Prior
發行者Institute of Electrical and Electronics Engineers Inc.
頁面74-77
頁數4
ISBN(電子)9781728158396
DOIs
出版狀態Published - 10月 2019
事件8th International Conference on Innovation, Communication and Engineering, ICICE 2019 - Zhengzhou, Henan Province, China
持續時間: 25 10月 201930 10月 2019

出版系列

名字Proceedings of the 2019 8th International Conference on Innovation, Communication and Engineering, ICICE 2019

Conference

Conference8th International Conference on Innovation, Communication and Engineering, ICICE 2019
國家/地區China
城市Zhengzhou, Henan Province
期間25/10/1930/10/19

指紋

深入研究「Increasing PE Utilization with a SW/HW Co-Design Technique for Sparse Convolutional Neural Networks」主題。共同形成了獨特的指紋。

引用此