Performance Prediction of Large-Scale 1S1R Resistive Memory Array Using Machine Learning

Zizhen Jiang, Peng Huang, Liang Zhao, Shahar Kvatinsky, Shimeng Yu, Xiaoyan Liu, Jinfeng Kang, Yoshio Nishi, H. S Philip Wong

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

5 Citations (Scopus)

Abstract

A methodology to analyze device-to-circuit characteristics and predict memory array performance is presented. With a five- parameter characterization of the selection device and a compact model of RRAM, we are able to capture the behaviors of reported selection devices and simulate 1S1R cell/array performance with RRAM compact modeling using HSPICE. To predict the performance of the memory array for a variety of selectors, machine-learning algorithms are employed, using device characteristics and circuit simulation results as the training data. The influence of selector parameters on the 1S1R cell and array behavior is investigated and projected to large Gbit arrays. The machine learning methods enable time-efficient and accurate estimates of 1S1R array performance to guide large-scale memory design.

Original languageEnglish (US)
Title of host publication2015 IEEE 7th International Memory Workshop, IMW 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781467369312
DOIs
StatePublished - Jul 2 2015
Event2015 7th IEEE International Memory Workshop, IMW 2015 - Monterey, United States
Duration: May 17 2015May 20 2015

Other

Other2015 7th IEEE International Memory Workshop, IMW 2015
CountryUnited States
CityMonterey
Period5/17/155/20/15

Fingerprint

Learning systems
Data storage equipment
Circuit simulation
Learning algorithms
Networks (circuits)
RRAM

Keywords

  • 1S1R
  • crossbar array
  • machine learning
  • prediction
  • RRAM
  • selector

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software
  • Electrical and Electronic Engineering
  • Computer Science Applications

Cite this

Jiang, Z., Huang, P., Zhao, L., Kvatinsky, S., Yu, S., Liu, X., ... Wong, H. S. P. (2015). Performance Prediction of Large-Scale 1S1R Resistive Memory Array Using Machine Learning. In 2015 IEEE 7th International Memory Workshop, IMW 2015 [7150302] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IMW.2015.7150302

Performance Prediction of Large-Scale 1S1R Resistive Memory Array Using Machine Learning. / Jiang, Zizhen; Huang, Peng; Zhao, Liang; Kvatinsky, Shahar; Yu, Shimeng; Liu, Xiaoyan; Kang, Jinfeng; Nishi, Yoshio; Wong, H. S Philip.

2015 IEEE 7th International Memory Workshop, IMW 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7150302.

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

Jiang, Z, Huang, P, Zhao, L, Kvatinsky, S, Yu, S, Liu, X, Kang, J, Nishi, Y & Wong, HSP 2015, Performance Prediction of Large-Scale 1S1R Resistive Memory Array Using Machine Learning. in 2015 IEEE 7th International Memory Workshop, IMW 2015., 7150302, Institute of Electrical and Electronics Engineers Inc., 2015 7th IEEE International Memory Workshop, IMW 2015, Monterey, United States, 5/17/15. https://doi.org/10.1109/IMW.2015.7150302
Jiang Z, Huang P, Zhao L, Kvatinsky S, Yu S, Liu X et al. Performance Prediction of Large-Scale 1S1R Resistive Memory Array Using Machine Learning. In 2015 IEEE 7th International Memory Workshop, IMW 2015. Institute of Electrical and Electronics Engineers Inc. 2015. 7150302 https://doi.org/10.1109/IMW.2015.7150302
Jiang, Zizhen ; Huang, Peng ; Zhao, Liang ; Kvatinsky, Shahar ; Yu, Shimeng ; Liu, Xiaoyan ; Kang, Jinfeng ; Nishi, Yoshio ; Wong, H. S Philip. / Performance Prediction of Large-Scale 1S1R Resistive Memory Array Using Machine Learning. 2015 IEEE 7th International Memory Workshop, IMW 2015. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{878087232912410bb7e0ed3e27d2c2f6,
title = "Performance Prediction of Large-Scale 1S1R Resistive Memory Array Using Machine Learning",
abstract = "A methodology to analyze device-to-circuit characteristics and predict memory array performance is presented. With a five- parameter characterization of the selection device and a compact model of RRAM, we are able to capture the behaviors of reported selection devices and simulate 1S1R cell/array performance with RRAM compact modeling using HSPICE. To predict the performance of the memory array for a variety of selectors, machine-learning algorithms are employed, using device characteristics and circuit simulation results as the training data. The influence of selector parameters on the 1S1R cell and array behavior is investigated and projected to large Gbit arrays. The machine learning methods enable time-efficient and accurate estimates of 1S1R array performance to guide large-scale memory design.",
keywords = "1S1R, crossbar array, machine learning, prediction, RRAM, selector",
author = "Zizhen Jiang and Peng Huang and Liang Zhao and Shahar Kvatinsky and Shimeng Yu and Xiaoyan Liu and Jinfeng Kang and Yoshio Nishi and Wong, {H. S Philip}",
year = "2015",
month = "7",
day = "2",
doi = "10.1109/IMW.2015.7150302",
language = "English (US)",
isbn = "9781467369312",
booktitle = "2015 IEEE 7th International Memory Workshop, IMW 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Performance Prediction of Large-Scale 1S1R Resistive Memory Array Using Machine Learning

AU - Jiang, Zizhen

AU - Huang, Peng

AU - Zhao, Liang

AU - Kvatinsky, Shahar

AU - Yu, Shimeng

AU - Liu, Xiaoyan

AU - Kang, Jinfeng

AU - Nishi, Yoshio

AU - Wong, H. S Philip

PY - 2015/7/2

Y1 - 2015/7/2

N2 - A methodology to analyze device-to-circuit characteristics and predict memory array performance is presented. With a five- parameter characterization of the selection device and a compact model of RRAM, we are able to capture the behaviors of reported selection devices and simulate 1S1R cell/array performance with RRAM compact modeling using HSPICE. To predict the performance of the memory array for a variety of selectors, machine-learning algorithms are employed, using device characteristics and circuit simulation results as the training data. The influence of selector parameters on the 1S1R cell and array behavior is investigated and projected to large Gbit arrays. The machine learning methods enable time-efficient and accurate estimates of 1S1R array performance to guide large-scale memory design.

AB - A methodology to analyze device-to-circuit characteristics and predict memory array performance is presented. With a five- parameter characterization of the selection device and a compact model of RRAM, we are able to capture the behaviors of reported selection devices and simulate 1S1R cell/array performance with RRAM compact modeling using HSPICE. To predict the performance of the memory array for a variety of selectors, machine-learning algorithms are employed, using device characteristics and circuit simulation results as the training data. The influence of selector parameters on the 1S1R cell and array behavior is investigated and projected to large Gbit arrays. The machine learning methods enable time-efficient and accurate estimates of 1S1R array performance to guide large-scale memory design.

KW - 1S1R

KW - crossbar array

KW - machine learning

KW - prediction

KW - RRAM

KW - selector

UR - http://www.scopus.com/inward/record.url?scp=84939504935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939504935&partnerID=8YFLogxK

U2 - 10.1109/IMW.2015.7150302

DO - 10.1109/IMW.2015.7150302

M3 - Conference contribution

AN - SCOPUS:84939504935

SN - 9781467369312

BT - 2015 IEEE 7th International Memory Workshop, IMW 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -