An energy efficient all-digital time-domain compute-in-memory macro optimized for binary neural networks

J Lou, F Freye, C Lanius… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The deployment of neural networks on edge devices has created a growing need for energy-
efficient computing. In this paper, we propose an all-digital standard cell-based time-domain …

Architecture-circuit-technology co-optimization for resistive random access memory-based computation-in-memory chips

Y Liu, B Gao, J Tang, H Wu, H Qian - Science China Information Sciences, 2023 - Springer
Abstract Computation-in-memory (CIM) chips offer an energy-efficient approach to artificial
intelligence computing workloads. Resistive random-access memory (RRAM)-based CIM …

DS-CIM: A 40nm Asynchronous Dual-Spike Driven, MRAM Compute-In-Memory Macro for Spiking Neural Network

H Fu, Y Huang, T Chen, C Fu, H Ren… - … on Circuits and …, 2024 - ieeexplore.ieee.org
Compute-in-memory (CIM) based on emerging nonvolatile memory (eNVM) is an effective
way to deploy neural networks to low-power edge devices for both storage and computation …

SSM-CIM: An Efficient CIM Macro Featuring Single-Step Multi-bit MAC Computation for CNN Edge Inference

H Zhang, S He, X Lu, X Guo, S Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Compute-in-memory (CIM) is a promising approach to solving the memory-wall problem
existing in traditional computing architectures. In this paper, we introduce SSM-CIM, a …

A 578-TOPS/W RRAM-based binary convolutional neural network macro for tiny AI edge devices

L Wang, Y Zhang, P Wang, J Yang… - … Transactions on Very …, 2024 - ieeexplore.ieee.org
The novel nonvolatile computing-in-memory (nvCIM) technology enables data to be stored
and processed in situ, providing a feasible solution for the widespread deployment of …

Spin device-based image edge detection architecture for neuromorphic computing

G Verma, S Soni, BK Kaushik - Nanotechnology, 2023 - iopscience.iop.org
Artificial intelligence and deep learning today are utilized for several applications namely
image processing, smart surveillance, edge computing, and so on. The hardware …

[HTML][HTML] Design of a low-power Digital-to-Pulse Converter (DPC) for in-memory-computing applications

K Humood, Y Pan, S Wang, A Serb… - Microelectronics …, 2024 - Elsevier
Data converters such as analog-to-digital converters (ADCs), digital-to-analog converters
(DACs), digital-to-time converters (DTCs), time-to-digital converters (TDCs), among others …

GemIMC: A Configurable HW Architecture for Technology Agnostic IMC based NN Inference

E Taly, R Guizzetti, P Urard… - 2024 IFIP/IEEE 32nd …, 2024 - ieeexplore.ieee.org
This paper presents GemIMC, a High Level Synthesis (HLS) based configurable digital unit
architecture for accelerating Neural Networks (NN) at the edge using In Memory Computing …

Straightforward data transfer in a blockwise dataflow for an analog RRAM-based CIM system

Y Liu, B Gao, P Yao, Q Liu, Q Zhang, D Wu… - Frontiers in …, 2023 - frontiersin.org
Analog resistive random-access memory (RRAM)-based computation-in-memory (CIM)
technology is promising for constructing artificial intelligence (AI) with high energy efficiency …

Heterogeneous 2D Memristor Array and Silicon Selector for Compute-in-Memory Hardware in Convolution Neural Networks

KW Ang, S Li, S Jain, H Zheng, L Li, X Fong - 2024 - researchsquare.com
Memristor crossbar arrays (CBAs) based on two-dimensional (2D) materials have emerged
as a potential solution to overcome the limitations of energy consumption and latency …