In-Memory Computing: Advances and prospects

By Naveen Verma, Hongyang Jia, Hossein Valavi, Yinqi Tang, Murat Ozatay, Lung-Yen Chen, Bonan Zhang, Peter Deaville. IEEE Solid-State Circuits Magazine, 2019

378 citations recorded by the source corpus.

High-dimensionality matrix-vector multiplication (MVM) is a dominant kernel in signal-processing and machine-learning computations that are being deployed in a range of energy- and throughput-constrained applications. In-memory computing (IMC) exploits the structural alignment between a dense 2D array of bit cells and the dataflow in MVM, enabling opportunities to address computational energy and throughput. Recent prototypes have demonstrated the potential for 10 × benefits in both metrics. However, fitting computation within an array of constrained bit-cell circuits imposes a number of challenges, including the need for analog computation, efficient interfacing with conventional digital accelerators (enabling the required programmability), and efficient virtualization of the hardware to map software. This article provides an overview of the fundamentals of IMC to better explain these challenges and then identifies promising paths forward among the wide range of emerging research.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/176df808669b51ad2d07b6defdb46d6300ba399e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Abu Sebastian
2. A. Eltawil
3. Evangelos Eleftheriou
4. M. Le Gallo

In Electrical and Electronic Engineering

1. Abu Sebastian
2. M. Le Gallo
3. Evangelos Eleftheriou
4. A. Eltawil
5. Wenhao Song

Citations in the corpus

• Hardware implementation of memristor-based artificial neural networks (2024, positive): “The proposed circuit comprises 4 kb synapses fabricated in a 65 nm CMOS processand reported anenergy ef fi ciencyof 55.8 TOPS per W. Incases where x is non-binary, one approach is to employ capacitors in addition to the SRAM cells 76,77,79 , involving a three-step process.”
• Memory devices and applications for in-memory computing (2020, background): “NaTuRe NaNoTecHNology This non-volatile accumulative behaviour, in spite of its nonlinear and stochastic nature, can be exploited in several applications, such as training deep neural networks, where the conductance values need to be incrementally modified.”