A nanoribbon device for analog phase change memory targeting neural network applications

Abstract

Phase change memory (PCM) is one of the most mature technologies for non-von Neumann computing. However, abrupt amorphization becomes a barrier for training artificial neural networks, due to limitations of the inherent operational mechanism of phase change materials. The devices can achieve a gradual conductance change in the crystallization process, while the conductance change for amorphization process is much more abrupt. This work presents a possible explanation for the RESET abrupt change issue in T-shaped devices, based on the analysis of the volume and connectivity of the amorphous and crystalline regions. Using this model, a nanoribbon device for analog PCM targeting neural network applications is designed, fabricated, and characterized. The designed device can realize a gradual RESET without changing the amplitude and width of RESET pulses. Using a nanoribbon device as a single synapse in the designed array reduces the number of SET operations needed to achieve the same accuracy in convolutional neural network simulation by 75%, which implies a significant reduction in power and time consumption. This work provides an effective way to implement gradual RESET for PCM devices.