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

Chien Yu Lin, Bo-Cheng Lai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

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).

Original languageEnglish
Title of host publicationASP-DAC 2018 - 23rd Asia and South Pacific Design Automation Conference, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages105-110
Number of pages6
ISBN (Electronic)9781509006021
DOIs
StatePublished - 20 Feb 2018
Event23rd Asia and South Pacific Design Automation Conference, ASP-DAC 2018 - Jeju, Korea, Republic of
Duration: 22 Jan 201825 Jan 2018

Publication series

NameProceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC
Volume2018-January

Conference

Conference23rd Asia and South Pacific Design Automation Conference, ASP-DAC 2018
CountryKorea, Republic of
CityJeju
Period22/01/1825/01/18

Fingerprint Dive into the research topics of 'Supporting compressed-sparse activations and weights on SIMD-like accelerator for sparse convolutional neural networks'. Together they form a unique fingerprint.

Cite this