Programming Protocol Optimization for Analog Weight Tuning in Resistive Memories

Ligang Gao; Pai Yu Chen; Shimeng Yu

doi:10.1109/LED.2015.2481819

Programming Protocol Optimization for Analog Weight Tuning in Resistive Memories

Ligang Gao, Pai Yu Chen, Shimeng Yu

Research output: Contribution to journal › Article › peer-review

79 Scopus citations

Abstract

Analog weight tuning in resistive memories is attractive for multilevel operation and neuro-inspired computing. To tune the device conductance to the desired states as fast as possible without sacrificing the accuracy, we propose an optimization programming protocol by adjusting the pulse amplitude incremental steps, the pulsewidth incremental steps, and the start voltages. Our experimental results on HfO_x-based resistive memories indicate that avoiding over-reset by appropriate programming parameters is critical for fast convergence of the conductance tuning. The over-reset behavior is caused by the stochastic nature of filament formation and rupture, as simulated by a 1-D filament model.

Original language	English (US)
Article number	7275091
Pages (from-to)	1157-1159
Number of pages	3
Journal	IEEE Electron Device Letters
Volume	36
Issue number	11
DOIs	https://doi.org/10.1109/LED.2015.2481819
State	Published - Nov 1 2015

Keywords

RRAM
multilevel
programming scheme

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Access to Document

10.1109/LED.2015.2481819

Cite this

@article{e646995cdb51471b80cf497074e7cdec,

title = "Programming Protocol Optimization for Analog Weight Tuning in Resistive Memories",

abstract = "Analog weight tuning in resistive memories is attractive for multilevel operation and neuro-inspired computing. To tune the device conductance to the desired states as fast as possible without sacrificing the accuracy, we propose an optimization programming protocol by adjusting the pulse amplitude incremental steps, the pulsewidth incremental steps, and the start voltages. Our experimental results on HfOx-based resistive memories indicate that avoiding over-reset by appropriate programming parameters is critical for fast convergence of the conductance tuning. The over-reset behavior is caused by the stochastic nature of filament formation and rupture, as simulated by a 1-D filament model.",

keywords = "RRAM, multilevel, programming scheme",

author = "Ligang Gao and Chen, {Pai Yu} and Shimeng Yu",

note = "Publisher Copyright: {\textcopyright} 1980-2012 IEEE.",

year = "2015",

month = nov,

day = "1",

doi = "10.1109/LED.2015.2481819",

language = "English (US)",

volume = "36",

pages = "1157--1159",

journal = "IEEE Electron Device Letters",

issn = "0741-3106",

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

number = "11",

}

TY - JOUR

T1 - Programming Protocol Optimization for Analog Weight Tuning in Resistive Memories

AU - Gao, Ligang

AU - Chen, Pai Yu

AU - Yu, Shimeng

PY - 2015/11/1

Y1 - 2015/11/1

N2 - Analog weight tuning in resistive memories is attractive for multilevel operation and neuro-inspired computing. To tune the device conductance to the desired states as fast as possible without sacrificing the accuracy, we propose an optimization programming protocol by adjusting the pulse amplitude incremental steps, the pulsewidth incremental steps, and the start voltages. Our experimental results on HfOx-based resistive memories indicate that avoiding over-reset by appropriate programming parameters is critical for fast convergence of the conductance tuning. The over-reset behavior is caused by the stochastic nature of filament formation and rupture, as simulated by a 1-D filament model.

AB - Analog weight tuning in resistive memories is attractive for multilevel operation and neuro-inspired computing. To tune the device conductance to the desired states as fast as possible without sacrificing the accuracy, we propose an optimization programming protocol by adjusting the pulse amplitude incremental steps, the pulsewidth incremental steps, and the start voltages. Our experimental results on HfOx-based resistive memories indicate that avoiding over-reset by appropriate programming parameters is critical for fast convergence of the conductance tuning. The over-reset behavior is caused by the stochastic nature of filament formation and rupture, as simulated by a 1-D filament model.

KW - RRAM

KW - multilevel

KW - programming scheme

UR - http://www.scopus.com/inward/record.url?scp=84946552385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946552385&partnerID=8YFLogxK

U2 - 10.1109/LED.2015.2481819

DO - 10.1109/LED.2015.2481819

M3 - Article

AN - SCOPUS:84946552385

SN - 0741-3106

VL - 36

SP - 1157

EP - 1159

JO - IEEE Electron Device Letters

JF - IEEE Electron Device Letters

IS - 11

M1 - 7275091

ER -

Programming Protocol Optimization for Analog Weight Tuning in Resistive Memories

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this