Memristive technologies for data storage, computation, encryption, and radio-frequency communication

M Lanza, A Sebastian, WD Lu, M Le Gallo, MF Chang… - Science, 2022 - science.org
Memristive devices, which combine a resistor with memory functions such that voltage
pulses can change their resistance (and hence their memory state) in a nonvolatile manner …

Recent advances and future prospects for memristive materials, devices, and systems

MK Song, JH Kang, X Zhang, W Ji, A Ascoli… - ACS …, 2023 - ACS Publications
Memristive technology has been rapidly emerging as a potential alternative to traditional
CMOS technology, which is facing fundamental limitations in its development. Since oxide …

[HTML][HTML] A compute-in-memory chip based on resistive random-access memory

W Wan, R Kubendran, C Schaefer, SB Eryilmaz… - Nature, 2022 - nature.com
Realizing increasingly complex artificial intelligence (AI) functionalities directly on edge
devices calls for unprecedented energy efficiency of edge hardware. Compute-in-memory …

Deep physical neural networks trained with backpropagation

LG Wright, T Onodera, MM Stein, T Wang… - Nature, 2022 - nature.com
Deep-learning models have become pervasive tools in science and engineering. However,
their energy requirements now increasingly limit their scalability. Deep-learning …

A 64-core mixed-signal in-memory compute chip based on phase-change memory for deep neural network inference

M Le Gallo, R Khaddam-Aljameh, M Stanisavljevic… - Nature …, 2023 - nature.com
Analogue in-memory computing (AIMC) with resistive memory devices could reduce the
latency and energy consumption of deep neural network inference tasks by directly …

[HTML][HTML] An analog-AI chip for energy-efficient speech recognition and transcription

S Ambrogio, P Narayanan, A Okazaki, A Fasoli… - Nature, 2023 - nature.com
Abstract Models of artificial intelligence (AI) that have billions of parameters can achieve
high accuracy across a range of tasks,, but they exacerbate the poor energy efficiency of …

A review of memristor: material and structure design, device performance, applications and prospects

Y **ao, B Jiang, Z Zhang, S Ke, Y **… - … and Technology of …, 2023 - Taylor & Francis
With the booming growth of artificial intelligence (AI), the traditional von Neumann
computing architecture based on complementary metal oxide semiconductor devices are …

Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators

MJ Rasch, C Mackin, M Le Gallo, A Chen… - Nature …, 2023 - nature.com
Analog in-memory computing—a promising approach for energy-efficient acceleration of
deep learning workloads—computes matrix-vector multiplications but only approximately …

Hardware implementation of memristor-based artificial neural networks

F Aguirre, A Sebastian, M Le Gallo, W Song… - Nature …, 2024 - nature.com
Artificial Intelligence (AI) is currently experiencing a bloom driven by deep learning (DL)
techniques, which rely on networks of connected simple computing units operating in …

Compute in‐memory with non‐volatile elements for neural networks: A review from a co‐design perspective

W Haensch, A Raghunathan, K Roy… - Advanced …, 2023 - Wiley Online Library
Deep learning has become ubiquitous, touching daily lives across the globe. Today,
traditional computer architectures are stressed to their limits in efficiently executing the …