A configurable multi-precision CNN computing framework based on single bit RRAM

Z Zhu, H Sun, Y Lin, G Dai, L ** with shifted and duplicated kernel
Y Zhang, G He, G Wang, Y Li - IEEE Transactions on Computer …, 2020 - ieeexplore.ieee.org
The conventional map** method between RRAM array and convolutional weights faces
two key challenges: 1) nonoptimal energy efficiency and 2) RRAM's temporal variation. To …

Gibbon: Efficient co-exploration of NN model and processing-in-memory architecture

H Sun, C Wang, Z Zhu, X Ning, G Dai… - … , Automation & Test …, 2022 - ieeexplore.ieee.org
The memristor-based Processing-In-Memory (PIM) architectures have shown great potential
to boost the computing energy efficiency of Neural Networks (NNs). Existing work …

MAX2: An ReRAM-Based Neural Network Accelerator That Maximizes Data Reuse and Area Utilization

M Mao, X Peng, R Liu, J Li, S Yu… - IEEE Journal on …, 2019 - ieeexplore.ieee.org
Although recent advances in resistive random access memory (ReRAM)-based accelerator
designs for deep convolutional neural networks (CNNs) offer energy-efficiency …

BRAHMS: Beyond conventional RRAM-based neural network accelerators using hybrid analog memory system

T Song, X Chen, X Zhang, Y Han - 2021 58th ACM/IEEE …, 2021 - ieeexplore.ieee.org
Accelerating convolutional neural networks (CNNs) with resistive random-access memory
(RRAM) based processing-in-memory systems has been recognized as a promising …

Design-technology co-optimization for NVM-based neuromorphic processing elements

S Song, A Balaji, A Das, N Kandasamy - ACM transactions on embedded …, 2022 - dl.acm.org
An emerging use case of machine learning (ML) is to train a model on a high-performance
system and deploy the trained model on energy-constrained embedded systems …