@inproceedings{8961b53f95a443c8ba15b851ba3c2b1b,
title = "Alleviating Bottlenecks for DNN Execution on GPUs via Opportunistic Computing",
abstract = "Edge computing and IoT applications are severely constrained by limited hardware resource. This makes memory-consuming DNN (Deep Neural Network) frameworks not applicable to edge computing. Simple algorithms such as direct convolution are finding their way in embedded machine learning. As one of the most widely used platforms for DNN acceleration, GPUs face the bottleneck of on-chip bandwidth. This work introduces a GPU DNN execution architecture that can relieve the on-chip bandwidth bottleneck by reducing data movement through opportunistic computing. We first investigate data access patterns in the hardware's view. Then we propose two opportunistic computing techniques to predictably perform computation when data is available with the help of assistant warps. By moving computation to data, our techniques are able to significantly reduce data movement and relieve the DNN execution bottleneck. Our evaluation results show that the proposed technique can improve DNN application performance as much as 55%.",
author = "Xianwei Cheng and Hui Zhao and Mahmut Kandemir and Saraju Mohanty and Beilei Jiang",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 21st International Symposium on Quality Electronic Design, ISQED 2020 ; Conference date: 25-03-2020 Through 26-03-2020",
year = "2020",
month = mar,
doi = "10.1109/ISQED48828.2020.9136967",
language = "English (US)",
series = "Proceedings - International Symposium on Quality Electronic Design, ISQED",
publisher = "IEEE Computer Society",
pages = "261--267",
booktitle = "Proceedings of the 21st International Symposium on Quality Electronic Design, ISQED 2020",
address = "United States",
}