Low Energy Domain Wall Memory Based Convolution Neural Network Design with Optimizing MAC Architecture
Running a convolutional neural network (CNN) algorithm using dedicated integrated circuits (ICs) on real-time portable applications is mainly restricted by slow performance and large power consumption. The power and delay are mainly due to external memory access, which incurs considerable energy consumption and bandwidth issues. In this paper, we propose an efficient convolution layer design using domain wall memory (DWM) for eliminating external memory access in image sensor embedded applications. A low energy access scheme using tag is employed to further reduce power consumption. The experimental results show that the proposed CNN architecture achieves 11.2% memory energy savings and 21.8% of MAC operation reduction compared to conventional architecture.
Paper
Full text
Low Energy Domain Wall Memory Based Convolution Neural Network Design with Optimizing MAC Architecture
Semantic Scholar · Computer Science · 2021
Abstract
Running a convolutional neural network (CNN) algorithm using dedicated integrated circuits (ICs) on real-time portable applications is mainly restricted by slow performance and large power consumption. The power and delay are mainly due to external memory access, which incurs considerable energy consumption and bandwidth issues. In this paper, we propose an efficient convolution layer design using domain wall memory (DWM) for eliminating external memory access in image sensor embedded applications. A low energy access scheme using tag is employed to further reduce power consumption. The experimental results show that the proposed CNN architecture achieves 11.2% memory energy savings and 21.8% of MAC operation reduction compared to conventional architecture.