An Energy-Efficient Precision-Scalable ConvNet Processor in 40-nm CMOS
Top Cited Papers
- 29 December 2016
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 52 (4), 903-914
- https://doi.org/10.1109/jssc.2016.2636225
Abstract
A precision-scalable processor for low-power ConvNets or convolutional neural networks is implemented in a 40-nm CMOS technology. To minimize energy consumption while maintaining throughput, this paper is the first to implement dynamic precision and energy scaling and exploit the sparsity of convolutions in a dedicated processor architecture. The processor's 256 parallel processing units achieve a peak 102 GOPS running at 204 MHz and 1.1 V. It is fully C-programmable through a custom generated compiler and consumes 25-287 mW at 204 MHz and a scaling efficiency between 0.3 and 2.7 effective TOPS/W. It achieves 47 frames/s on the convolutional layers of the AlexNet benchmark, consuming only 76 mW. This system hereby outperforms the state-of-the-art up to five times in energy efficiency.Keywords
Funding Information
- Research Foundation – Flanders
- Intel Corporation
This publication has 21 references indexed in Scilit:
- Energy-efficient ConvNets through approximate computingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- DVAS: Dynamic Voltage Accuracy Scaling for increased energy-efficiency in approximate computingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- ShiDianNaoPublished by Association for Computing Machinery (ACM) ,2015
- Long-term recurrent convolutional networks for visual recognition and descriptionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Fully convolutional networks for semantic segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- DaDianNao: A Machine-Learning SupercomputerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Approximate computing: An integrated hardware approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Memory-centric accelerator design for Convolutional Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- A dynamic voltage scaled microprocessor systemIEEE Journal of Solid-State Circuits, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998