A software technique to enhance register utilization of Convolutional Neural Networks on GPGPUs

Che Huai Lin, An Ting Cheng, Bo-Cheng Lai

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

CNNs (Convolutional Neural Networks) have demonstrated superior results in a wide range of applications. However, the time-consuming convolution operations required by CNNs pose great challenges to designers. GPGPUs (General Purpose Graphic Processing Units) have been widely used to exploiting the massive parallelism of convolution operations. This paper proposes a software-based loop-unrolling technique to enhance the data usage on the registers and significantly improve the overall performance. The experimental results on a cycle-Accurate GPGPU simulator have shown that the proposed technique can achieve up to 71% performance enhancement when compared with the reference design.

原文English
主出版物標題Proceedings of the 2017 IEEE International Conference on Applied System Innovation
主出版物子標題Applied System Innovation for Modern Technology, ICASI 2017
編輯Teen-Hang Meen, Artde Donald Kin-Tak Lam, Stephen D. Prior
發行者Institute of Electrical and Electronics Engineers Inc.
頁面614-617
頁數4
ISBN(電子)9781509048977
DOIs
出版狀態Published - 21 7月 2017
事件2017 IEEE International Conference on Applied System Innovation, ICASI 2017 - Sapporo, Japan
持續時間: 13 5月 201717 5月 2017

出版系列

名字Proceedings of the 2017 IEEE International Conference on Applied System Innovation: Applied System Innovation for Modern Technology, ICASI 2017

Conference

Conference2017 IEEE International Conference on Applied System Innovation, ICASI 2017
國家/地區Japan
城市Sapporo
期間13/05/1717/05/17

指紋

深入研究「A software technique to enhance register utilization of Convolutional Neural Networks on GPGPUs」主題。共同形成了獨特的指紋。

引用此