16018

YodaNN: An Ultra-Low Power Convolutional Neural Network Accelerator Based on Binary Weights

Renzo Andri, Lukas Cavigelli, Davide Rossi, Luca Benini
Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland
arXiv:1606.05487 [cs.AR], (17 Jun 2016)

@article{andri2016yodann,

   title={YodaNN: An Ultra-Low Power Convolutional Neural Network Accelerator Based on Binary Weights},

   author={Andri, Renzo and Cavigelli, Lukas and Rossi, Davide and Benini, Luca},

   year={2016},

   month={jun},

   archivePrefix={"arXiv"},

   primaryClass={cs.AR}

}

Download Download (PDF)   View View   Source Source   

1768

views

Convolutional Neural Networks (CNNs) have revolutionized the world of image classification over the last few years, pushing the computer vision close beyond human accuracy. The required computational effort of CNNs today requires power-hungry parallel processors and GP-GPUs. Recent efforts in designing CNN Application-Specific Integrated Circuits (ASICs) and accelerators for System-On-Chip (SoC) integration have achieved very promising results. Unfortunately, even these highly optimized engines are still above the power envelope imposed by mobile and deeply embedded applications and face hard limitations caused by CNN weight I/O and storage. On the algorithmic side, highly competitive classification accuracy can be achieved by properly training CNNs with binary weights. This novel algorithm approach brings major optimization opportunities in the arithmetic core by removing the need for the expensive multiplications as well as in the weight storage and I/O costs. In this work, we present a HW accelerator optimized for BinaryConnect CNNs that achieves 1510 GOp/s on a core area of only 1.33 MGE and with a power dissipation of 153 mW in UMC 65 nm technology at 1.2 V. Our accelerator outperforms state-of-the-art performance in terms of ASIC energy efficiency as well as area efficiency with 61.2 TOp/s/W and 1135 GOp/s/MGE, respectively.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: