GPU-based Acceleration of Deep Convolutional Neural Networks on Mobile Platforms
Sharif University of Technology
arXiv:1511.07376 [cs.DC], (23 Nov 2015)
@article{oskouei2015gpubased,
title={GPU-based Acceleration of Deep Convolutional Neural Networks on Mobile Platforms},
author={Oskouei, Seyyed Salar Latifi and Golestani, Hossein and Kachuee, Mohamad and Hashemi, Matin and Mohammadzade, Hoda and Ghiasi, Soheil},
year={2015},
month={nov},
archivePrefix={"arXiv"},
primaryClass={cs.DC}
}
Mobile applications running on wearable devices and smartphones can greatly benefit from accurate and scalable deep CNN-based machine learning algorithms. While mobile CPU performance does not match the intensive computational requirement of deep CNNs, the embedded GPU which already exists in many mobile platforms can be leveraged for acceleration of CNN computations on the local device and without the use of a cloud service. We present a GPU-based accelerated deep CNN engine for mobile platforms with upto 60X speedup.
November 25, 2015 by hgpu
