Supporting compressed-sparse activations and weights on SIMD-like accelerator for sparse convolutional neural networks

Chien Yu Lin, Bo-Cheng Lai

研究成果: Conference contribution同行評審

13 引文 斯高帕斯(Scopus)

摘要

Sparsity is widely observed in convolutional neural networks by zeroing a large portion of both activations and weights without impairing the result. By keeping the data in a compressed-sparse format, the energy consumption could be considerably cut down due to less memory traffic. However, the wide SIMD-like MAC engine adopted in many CNN accelerators can not support the compressed input due to the data misalignment. In this work, a novel Dual Indexing Module (DIM) is proposed to efficiently handle the alignment issue where activations and weights are both kept in compressed-sparse format. The DIM is implemented in a representative SIMD-like CNN accelerator, and able to exploit both compressed-sparse activations and weights. The synthesis results with 40nm technology have shown that DIM can enhance up to 46% of energy consumption and 55.4% Energy-Delay-Product (EDP).

原文English
主出版物標題ASP-DAC 2018 - 23rd Asia and South Pacific Design Automation Conference, Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面105-110
頁數6
ISBN(電子)9781509006021
DOIs
出版狀態Published - 20 2月 2018
事件23rd Asia and South Pacific Design Automation Conference, ASP-DAC 2018 - Jeju, Korea, Republic of
持續時間: 22 1月 201825 1月 2018

出版系列

名字Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC
2018-January

Conference

Conference23rd Asia and South Pacific Design Automation Conference, ASP-DAC 2018
國家/地區Korea, Republic of
城市Jeju
期間22/01/1825/01/18

指紋

深入研究「Supporting compressed-sparse activations and weights on SIMD-like accelerator for sparse convolutional neural networks」主題。共同形成了獨特的指紋。

引用此