Sparse and Robust RRAM-based Efficient In-memory Computing for DNN Inference

Jian Meng, Injune Yeo, Wonbo Shim, Li Yang, Deliang Fan, Shimeng Yu, Jae Sun Seo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations


Resistive random-access memory (RRAM)-based in-memory computing (IMC) recently became a promising paradigm for efficient deep neural network acceleration. The multi-bit RRAM arrays provide dense storage and high throughput, whereas the physical non-ideality of the RRAM devices impairs the retention characteristics of the resistive cells, leading to accuracy degradation. On the algorithm side, various hardware-aware compression algorithms have been proposed to accelerate the computation of deep neural networks (DNNs) computation. However, most recent works individually consider the "model compression"and "hardware robustness". The impact of the RRAM non-ideality for the sparse model is still under-explored. In this work, we present a novel temperature-resilient RRAM-based IMC scheme for reliable DNN inference hardware. Based on the measurement from a 90nm RRAM prototype chip, we first explore the robustness of the sparse model under the different operating temperatures (25°C to 85°C). On top of that, we propose a novel robustness-aware pruning algorithm, then further enhance the model robustness with a novel sparsity-aware noise-injected fine-tuning. The proposed scheme achieves >92% CIFAR-10 inference accuracy after one-day operation, which is >37% higher than the state-of-art method.

Original languageEnglish (US)
Title of host publication2022 IEEE International Reliability Physics Symposium, IRPS 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665479509
StatePublished - 2022
Event2022 IEEE International Reliability Physics Symposium, IRPS 2022 - Dallas, United States
Duration: Mar 27 2022Mar 31 2022

Publication series

NameIEEE International Reliability Physics Symposium Proceedings
ISSN (Print)1541-7026


Conference2022 IEEE International Reliability Physics Symposium, IRPS 2022
Country/TerritoryUnited States


  • Convolutional neural network
  • data retention
  • in-memory computing
  • multilevel RRAM
  • structured pruning

ASJC Scopus subject areas

  • Engineering(all)


Dive into the research topics of 'Sparse and Robust RRAM-based Efficient In-memory Computing for DNN Inference'. Together they form a unique fingerprint.

Cite this