One-step regression and classification with cross-point resistive memory arrays

Resistive memories, also known as memristors (1), including resistive switching memory (RRAM) and phase-change memory (PCM), are emerging as a novel technology for high-density storage (2, 3), neuromorphic hardware (4, 5), and stochastic security primitives, such as random number generators (6, 7). Thanks to their ability to store analog values and to their excellent programming speed, resistive memories have also been demonstrated for executing in-memory computing (8–17), which eliminates the data transfer between the memory and the processing unit to improve the time and energy efficiency of computation. With a cross-point architecture, resistive memories can be naturally used to perform matrix-vector multiplication (MVM) by exploiting fundamental physical laws such as the Ohm's law and the Kirchhoff's law of electric circuits (8). Cross-point MVM has been shown to accelerate various data-intensive tasks, such as training and inference of deep neural networks (11–14), signal and image processing (15), and the iterative solution of a system of linear equations (16) or a differential equation (17). With a feedback circuit configuration, the cross-point array has been shown to solve systems of linear equations and calculate matrix eigenvectors in one step (18).