Optimization of Programming Pulse Shape for Vertical NAND Flash Memory Using Neural Networks

Abstract

We optimize the shape of the pulse to maximally increase threshold voltage ( ${V}_{\text {th}}\text {)}$ during the incremental step pulse programming (ISPP) of vertical NAND (V-NAND) flash memory using neural networks (NNs). NN is trained using data on the increase in ${V}_{\text {th}}$ of commercial V-NAND flash memory in response to randomly shaped programming pulses (PPs). The trained NN is utilized to optimize the shape of the PP. The principle behind the improvement in ${V}_{\text {th}}$ increase due to the optimized PP, as well as the improvement results, are confirmed through measurements. When the optimized PP is applied to ISPP operation, it results in a 37% increase in ISPP slope. Furthermore, the optimized PP exhibits lower program disturbance, indicating the potential for faster programming with lower energy consumption.