@inproceedings{de91ca78041c4c8293b345c6487ab0df,
title = "A software technique to enhance register utilization of Convolutional Neural Networks on GPGPUs",
abstract = "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.",
keywords = "CNN, Design and optimization, GPU",
author = "Lin, {Che Huai} and Cheng, {An Ting} and Bo-Cheng Lai",
year = "2017",
month = jul,
day = "21",
doi = "10.1109/ICASI.2017.7988499",
language = "English",
series = "Proceedings of the 2017 IEEE International Conference on Applied System Innovation: Applied System Innovation for Modern Technology, ICASI 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "614--617",
editor = "Teen-Hang Meen and Lam, {Artde Donald Kin-Tak} and Prior, {Stephen D.}",
booktitle = "Proceedings of the 2017 IEEE International Conference on Applied System Innovation",
address = "United States",
note = "null ; Conference date: 13-05-2017 Through 17-05-2017",
}