Energy-Efficient Precision-Scaled CNN Implementation With Dynamic Partial Reconfiguration

doi:10.1109/ACCESS.2022.3204704

Energy-Efficient Precision-Scaled CNN Implementation With Dynamic Partial Reconfiguration

2022-01-01

4

OA

AI

DOI：10.1109/ACCESS.2022.3204704

Original

Original request for help

Save

Abstract

En 中文

A convolutional neural network (CNN) classifies images with high accuracy. However, CNN operation requires a large number of computations which consume a significant amount of power when implemented on hardware. Precision scaling has been recently used to reduce the hardware requirements and power consumption. In this paper, we present an energy-efficient precision-scaled CNN (EEPS-CNN) architecture. Furthermore, the Field Programmable Gate Array (FPGA) is reconfigured during run time using Dynamic Partial Reconfiguration (DPR). If the battery level decreases, the EEPS-CNN design with the most appropriate power consumption is configured on the FPGA. DPR enables recognition applications to run at a low power budget while sacrificing minor accuracy instead of termination. The proposed architecture is implemented on Xilinx XC7Z020 FPGA and is evaluated on three datasets: MNIST, F-MNIST, and SVHN datasets. The results show a 2.2X, 2.39X, and 2.38X reduction in the energy consumption, respectively, while using only 7 bits to represent all inputs and network parameters. The accuracy of the proposed EEPS-CNN is only 0.53%, 3.67%, and 0.88% less than 32-bit floating-point architectures for MNIST, F-MNIST, and SVHN, respectively. Moreover, the results show up to 92.91X and 4.84X reductions in the power and energy consumption of the proposed EEPS-CNN compared to related designs developed for the MNIST dataset.

Keywords:

Convolutional neural networks

Field programmable gate arrays

Computer architecture

Convolution

Reconfiguration logic

Feature extraction

Power demand

Energy efficiency

Precision engineering

Approximate computing

convolutional neural network

dynamic partial reconfiguration

energy efficiency

precision scaling

Energy-Efficient Precision-Scaled CNN Implementation With Dynamic Partial Reconfiguration

Abstract

Journal

Organization