Fast and Energy-Efficient CNN Inference on IoT Devices

Mohammad Motamedi, Daniel Fong, Soheil Ghiasi
ECE Department, University of California, Davis
arXiv:1611.07151 [cs.DC], (22 Nov 2016)


   title={Fast and Energy-Efficient CNN Inference on IoT Devices},

   author={Motamedi, Mohammad and Fong, Daniel and Ghiasi, Soheil},






Convolutional Neural Networks (CNNs) exhibit remarkable performance in various machine learning tasks. As sensor-equipped internet of things (IoT) devices permeate into every aspect of modern life, it is increasingly important to run CNN inference, a computationally intensive application, on resource constrained devices. We present a technique for fast and energy-efficient CNN inference on mobile SoC platforms, which are projected to be a major player in the IoT space. We propose techniques for efficient parallelization of CNN inference targeting mobile GPUs, and explore the underlying tradeoffs. Experiments with running Squeezenet on three different mobile devices confirm the effectiveness of our approach. For further study, please refer to the project repository available on our GitHub page.
VN:F [1.9.22_1171]
Rating: 3.8/5 (4 votes cast)
Fast and Energy-Efficient CNN Inference on IoT Devices, 3.8 out of 5 based on 4 ratings

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: