Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference

Zhilu Ye; Rui Liu; Hugh Barnaby; Shimeng Yu

doi:10.1109/IRPS.2019.8720490

Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference

Zhilu Ye, Rui Liu, Hugh Barnaby, Shimeng Yu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

In this work, single event effects (SEEs) are analyzed in SRAM- and RRAM-based neuromorphic computing systems. SPICE simulation is employed to model single event upset (SEU) at the array level. Then SEU effects are mapped to the weight pattern change of a multi-layer perceptron (MLP), a representative artificial neural network for MNIST handwritten digit recognition. Simulations show that the RRAM-based MLP has less susceptibility to SEEs compared with the SRAM architecture. Improvements to the SRAM-based MLP reliability may be achieved by lowering bit-width and enlarging network size.

Original language	English (US)
Title of host publication	2019 IEEE International Reliability Physics Symposium, IRPS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538695043
DOIs	https://doi.org/10.1109/IRPS.2019.8720490
State	Published - May 22 2019
Event	2019 IEEE International Reliability Physics Symposium, IRPS 2019 - Monterey, United States Duration: Mar 31 2019 → Apr 4 2019

Publication series

Name	IEEE International Reliability Physics Symposium Proceedings
Volume	2019-March
ISSN (Print)	1541-7026

Conference

Conference	2019 IEEE International Reliability Physics Symposium, IRPS 2019
Country/Territory	United States
City	Monterey
Period	3/31/19 → 4/4/19

Keywords

Multi-layer perceptron
Neuromorphic computing
RRAM
SRAM
Single event upset

ASJC Scopus subject areas

Engineering(all)

Access to Document

10.1109/IRPS.2019.8720490

Cite this

Ye, Z., Liu, R., Barnaby, H., & Yu, S. (2019). Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference. In 2019 IEEE International Reliability Physics Symposium, IRPS 2019 [8720490] (IEEE International Reliability Physics Symposium Proceedings; Vol. 2019-March). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IRPS.2019.8720490

Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference. / Ye, Zhilu; Liu, Rui; Barnaby, Hugh et al.

2019 IEEE International Reliability Physics Symposium, IRPS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8720490 (IEEE International Reliability Physics Symposium Proceedings; Vol. 2019-March).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ye, Z, Liu, R, Barnaby, H & Yu, S 2019, Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference. in 2019 IEEE International Reliability Physics Symposium, IRPS 2019., 8720490, IEEE International Reliability Physics Symposium Proceedings, vol. 2019-March, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Reliability Physics Symposium, IRPS 2019, Monterey, United States, 3/31/19. https://doi.org/10.1109/IRPS.2019.8720490

Ye Z, Liu R, Barnaby H, Yu S. Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference. In 2019 IEEE International Reliability Physics Symposium, IRPS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8720490. (IEEE International Reliability Physics Symposium Proceedings). https://doi.org/10.1109/IRPS.2019.8720490

@inproceedings{a7fa10a566f34c9c9cdfac846f5d3264,

title = "Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference",

abstract = "In this work, single event effects (SEEs) are analyzed in SRAM- and RRAM-based neuromorphic computing systems. SPICE simulation is employed to model single event upset (SEU) at the array level. Then SEU effects are mapped to the weight pattern change of a multi-layer perceptron (MLP), a representative artificial neural network for MNIST handwritten digit recognition. Simulations show that the RRAM-based MLP has less susceptibility to SEEs compared with the SRAM architecture. Improvements to the SRAM-based MLP reliability may be achieved by lowering bit-width and enlarging network size.",

keywords = "Multi-layer perceptron, Neuromorphic computing, RRAM, SRAM, Single event upset",

author = "Zhilu Ye and Rui Liu and Hugh Barnaby and Shimeng Yu",

note = "Funding Information: This work was supported in part by DoD-DTRA under grant HDTRA1-17-1-0038. Funding Information: ACKNOWLEDGEMENT This work was supported in part by grant HDTRA1-17-1-0038. Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE International Reliability Physics Symposium, IRPS 2019 ; Conference date: 31-03-2019 Through 04-04-2019",

year = "2019",

month = may,

day = "22",

doi = "10.1109/IRPS.2019.8720490",

language = "English (US)",

series = "IEEE International Reliability Physics Symposium Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 IEEE International Reliability Physics Symposium, IRPS 2019",

}

TY - GEN

T1 - Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference

AU - Ye, Zhilu

AU - Liu, Rui

AU - Barnaby, Hugh

AU - Yu, Shimeng

N1 - Funding Information: This work was supported in part by DoD-DTRA under grant HDTRA1-17-1-0038. Funding Information: ACKNOWLEDGEMENT This work was supported in part by grant HDTRA1-17-1-0038. Publisher Copyright: © 2019 IEEE.

PY - 2019/5/22

Y1 - 2019/5/22

N2 - In this work, single event effects (SEEs) are analyzed in SRAM- and RRAM-based neuromorphic computing systems. SPICE simulation is employed to model single event upset (SEU) at the array level. Then SEU effects are mapped to the weight pattern change of a multi-layer perceptron (MLP), a representative artificial neural network for MNIST handwritten digit recognition. Simulations show that the RRAM-based MLP has less susceptibility to SEEs compared with the SRAM architecture. Improvements to the SRAM-based MLP reliability may be achieved by lowering bit-width and enlarging network size.

AB - In this work, single event effects (SEEs) are analyzed in SRAM- and RRAM-based neuromorphic computing systems. SPICE simulation is employed to model single event upset (SEU) at the array level. Then SEU effects are mapped to the weight pattern change of a multi-layer perceptron (MLP), a representative artificial neural network for MNIST handwritten digit recognition. Simulations show that the RRAM-based MLP has less susceptibility to SEEs compared with the SRAM architecture. Improvements to the SRAM-based MLP reliability may be achieved by lowering bit-width and enlarging network size.

KW - Multi-layer perceptron

KW - Neuromorphic computing

KW - RRAM

KW - SRAM

KW - Single event upset

UR - http://www.scopus.com/inward/record.url?scp=85066732435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066732435&partnerID=8YFLogxK

U2 - 10.1109/IRPS.2019.8720490

DO - 10.1109/IRPS.2019.8720490

M3 - Conference contribution

AN - SCOPUS:85066732435

T3 - IEEE International Reliability Physics Symposium Proceedings

BT - 2019 IEEE International Reliability Physics Symposium, IRPS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE International Reliability Physics Symposium, IRPS 2019

Y2 - 31 March 2019 through 4 April 2019

ER -

Evaluation of Single Event Effects in SRAM and RRAM Based Neuromorphic Computing System for Inference

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this