Spatio-Temporal Modeling for Flash Memory Channels Using Conditional Generative Nets
Simeng Zheng
Abstract:
Understanding the NAND flash memory channel has become more and more challenging due to the continually increasing cell density and decreasing device size. Modeling the spatio-temporal read voltages with complex distortions arising from the write and read mechanisms is essential for algorithm design in flash devices.
In this work, we propose a data-driven approach to modeling the spatio-temporal characteristics of NAND flash memory read voltages using conditional generative networks. The learned model reconstructs read voltages from an individual memory cell based on the program levels of the cell and its surrounding cells, as well as the specified program/erase (P/E) cycling time stamp. We evaluate the model over a range of time stamps using the cell read voltage distributions, the cell level error rates, and the relative frequency of errors for patterns most susceptible to inter-cell interference (ICI) effects. Moreover, we extend the generative modeling approach to the coded storage channel. We train the generative model with constrained program/read data via transferring knowledge from models pre-trained with pseudo-random data. The experimental results show that the model accurately captures the spatial and temporal features of the flash memory channel.