In-Memory Computing with Resistive Memory Circuits: Status and Outlook

Abstract

In-memory computing (IMC) refers to non-von Neumann architectures where data are processed in situ within the memory by taking advantage of physical laws. Among the memory devices that have been considered for IMC, the resistive switching memory (RRAM), also known as memristor, is one of the most promising technologies due to its relatively easy integration and scaling. RRAM devices have been explored for both memory and IMC applications, such as neural network accelerators and neuromorphic processors. This work presents the status and outlook on the RRAM for analog computing, where the precision of the encoded coefficients, such as the synaptic weights of a neural network, is one of the key requirements. We show the experimental study of the cycle-to-cycle variation of set and reset processes for HfO2-based RRAM, which indicate that gate-controlled pulses present the least variation in conductance. Assuming a constant variation of conductance σG, we then evaluate and compare various mapping schemes, including multilevel, binary, unary, redundant and slicing techniques. We present analytical formulas for the standard deviation of the conductance and the maximum number of bits that still satisfies a given maximum error. Finally, we discuss RRAM performance for various analog computing tasks compared to other computational memory devices. RRAM appears as one of the most promising devices in terms of scaling, accuracy and low-current operation.

Computing Nearer to Data

“…13 In addition to using PCM for neuromorphic arrays, there have been neuromorphic computing devices designed with resistive memories and magnetorestrictive RAM (MRAM) memories. 14,15 There is also a body of work on spintronic computation using spins rather than electric currents, 16 which can be in close proximity to MRAM memories. Higher speed analog computing, such as image recognition, is also possible using photonic in-memory computing.…”

High-Density Solid-State Memory Devices and Technologies

“…The first review paper in the Special Issue is by Pedretti and Ielmini [1] and summarizes the current status of analog in-memory computing with RRAM devices, representing a promising non-von Neumann computing approach. In the paper, the fundamentals of RRAM devices and of the new computing concept are first reviewed, highlighting the importance of achieving a tight control over the analog conductance of the resistive memory elements.…”

Multi-Input Logic-in-Memory for Ultra-Low Power Non-Von Neumann Computing

“…As the adoption of deep learning and neural networks is becoming more and more pervasive, the demand for energy efficient hardware accelerators is rapidly growing. When considering neural networks, the most effective way to improve energy efficiency is to avoid the VNB by performing computations in-memory [45][46][47][48]. A common approach exploits resistive memory crossbar arrays to implement in analog the vector matrix multiplication in a single step [45].…”