Demonstration of 3D Convolution Kernel Function Based on 8-Layer 3D Vertical Resistive Random Access Memory
Qiang Huo, Renjun Song, Dengyun Lei, Qing Luo, Zhenhua Wu, Zuheng Wu, Xiaojin Zhao, Feng Zhang, Ling Li, Ming Liu
Abstract
3D Convolutional Neural Networks (CNNs) has been widely used for medical image analysis such as magnetic resonance imaging (MRI) and video recognition due to their intrinsic 3D characteristics. This letter presents 3D convolution operations realized by an 8-layers 3D vertical resistive random access memory (VRRAM) under a field-programmable gate array (FPGA)-controlled relay-matrix based test platform. As an implementation, 3D Prewitt operators are used for edge surface detection of 3D version MNIST handwritten digits with 16 × 16 × 16 pixels. The experimental results show that 3D convolution kernels can be correctly implemented on our in-house 3D VRRAM with higher parallelism than the conventional architecture. Besides, the proposed 3D VRRAM meets the demands of low power and high capacity for 3D CNN accelerator, paving the way of 3D VRRAM-based processing-in-memory (PIM) architecture for 3D CNNs.