Power Efficient Tiny Yolo CNN Using Reduced Hardware Resources Based on Booth Multiplier and WALLACE Tree Adders
Open Access
- 7 July 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Circuits and Systems
- Vol. 1, 76-87
Abstract
Convolutional Neural Network (CNN) has attained high accuracy and it has been widely employed in image recognition tasks. In recent times, deep learning-based modern applications are evolving and it poses a challenge in research and development of hardware implementation. Therefore, hardware optimization for efficient accelerator design of CNN remains a challenging task. A key component of the accelerator design is a processing element (PE) that implements the convolution operation. To reduce the amount of hardware resources and power consumption, this article provides a new processing element design as an alternate solution for hardware implementation. Modified BOOTH encoding (MBE) multiplier and WALLACE tree-based adders are proposed to replace bulky MAC units and typical adder tree respectively. The proposed CNN accelerator design is tested on Zynq-706 FPGA board which achieves a throughput of 87.03 GOP/s for Tiny-YOLO-v2 architecture. The proposed design allows to reduce hardware costs by 24.5% achieving a power efficiency of 61.64 GOP/s/W that outperforms the previous designs.Keywords
Funding Information
- National Science and Technology Major Project (2016ZX01012101)
This publication has 40 references indexed in Scilit:
- Stacked Autoencoders Using Low-Power Accelerated Architectures for Object Recognition in Autonomous SystemsNeural Processing Letters, 2015
- A study of performance comparison of digital multipliers using 22nm strained silicon technology2015
- Design Options for Basic Building Blocks2011
- Learning long‐range vision for autonomous off‐road drivingJournal of Field Robotics, 2009
- Ultra Low-Voltage Low-Power CMOS 4-2 and 5-2 Compressors for Fast Arithmetic CircuitsIEEE Transactions on Circuits and Systems I: Regular Papers, 2004
- Multiplication2004
- Multiplication2004
- A fast parallel multiplier-accumulator using the modified Booth algorithmIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 2000
- High-speed Booth encoded parallel multiplier designIEEE Transactions on Computers, 2000
- M*N Booth encoded multiplier generator using optimized Wallace treesIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 1993