標題: Supporting Compressed-Sparse Activations and Weights on SIMD-like Accelerator for Sparse Convolutional Neural Networks
作者: Lin, Chien-Yu
Lai, Bo-Cheng
電子工程學系及電子研究所
Department of Electronics Engineering and Institute of Electronics
公開日期: 1-一月-2018
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).
URI: http://hdl.handle.net/11536/147112
ISSN: 2153-6961
期刊: 2018 23RD ASIA AND SOUTH PACIFIC DESIGN AUTOMATION CONFERENCE (ASP-DAC)
起始頁: 105
結束頁: 110
顯示於類別:會議論文