Field-free multistate spin–orbit torque devices for programmable image edge recognition circuit

The application of spin–orbit torque (SOT) devices to neuromorphic computing platforms is focused on the development of hardware circuit architectures. However, the inter-device variability, the integration modes of devices and peripheral circuits, and appropriate application scenarios are still unc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied physics letters 2024-09, Vol.125 (10)
Hauptverfasser: Yang, Liu, Li, Wendi, Zuo, Chao, Tao, Ying, Jin, Fang, Li, Huihui, Tang, RuJun, Dong, Kaifeng
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 10
container_start_page
container_title Applied physics letters
container_volume 125
creator Yang, Liu
Li, Wendi
Zuo, Chao
Tao, Ying
Jin, Fang
Li, Huihui
Tang, RuJun
Dong, Kaifeng
description The application of spin–orbit torque (SOT) devices to neuromorphic computing platforms is focused on the development of hardware circuit architectures. However, the inter-device variability, the integration modes of devices and peripheral circuits, and appropriate application scenarios are still unclear, limiting the development of SOT devices in neuromorphic computing. To solve this problem, this paper first proposes a circuit compensation scheme for the difference in resistance values of SOT devices, which solves this variability problem at the circuit level. Moreover, a synergistic scheme with the circuit is developed based on the correspondence between the multistate resistance characteristics of the SOT devices and a convolutional algorithm. To achieve this, a multichannel SOT convolutional kernel circuit architecture is built, which implements an image edge recognition application. Finally, based on a simulation model, an image edge recognition hardware circuit based on our CoPt-SOT devices is implemented, which is capable of performing image edge recognition with an accuracy of 96.33%. This scheme provides technical support and development prospects for SOT devices in neural network hardware applications.
doi_str_mv 10.1063/5.0220711
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1063_5_0220711</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3100319139</sourcerecordid><originalsourceid>FETCH-LOGICAL-c182t-3f2bd5253b37d46b454296edbb3b780e6223cba0cc6e706b4fb3ecf6916961373</originalsourceid><addsrcrecordid>eNp9kMFKAzEQhoMoWKsH3yDgSWFrJtPNdo9SrAoFL3peNtnZkrK7qUlW8OY7-IY-SSPt2csMw3zM_P_P2DWIGQiF9_lMSCkKgBM2AVEUGQIsTtlECIGZKnM4ZxchbNOYS8QJq1eWuiZrPRHvxy7aEOtIPOzs8Pv947y2kUfnP0biDX1aQ4G3zvOddxtf932tO-K2rzfEqUnFk3GbwUbrBm6sN6ONl-ysrbtAV8c-Ze-rx7flc7Z-fXpZPqwzAwsZM2ylbnKZo8aimSs9z-eyVNRojbpYCFJSotG1MEZRIdK-1UimVSWoUgEWOGU3h7tJW5IbYrV1ox_SywohuYcSsEzU7YEy3oXgqa12Pun3XxWI6i_BKq-OCSb27sAGY1MqydM_8B694XHf</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3100319139</pqid></control><display><type>article</type><title>Field-free multistate spin–orbit torque devices for programmable image edge recognition circuit</title><source>AIP Journals Complete</source><creator>Yang, Liu ; Li, Wendi ; Zuo, Chao ; Tao, Ying ; Jin, Fang ; Li, Huihui ; Tang, RuJun ; Dong, Kaifeng</creator><creatorcontrib>Yang, Liu ; Li, Wendi ; Zuo, Chao ; Tao, Ying ; Jin, Fang ; Li, Huihui ; Tang, RuJun ; Dong, Kaifeng</creatorcontrib><description>The application of spin–orbit torque (SOT) devices to neuromorphic computing platforms is focused on the development of hardware circuit architectures. However, the inter-device variability, the integration modes of devices and peripheral circuits, and appropriate application scenarios are still unclear, limiting the development of SOT devices in neuromorphic computing. To solve this problem, this paper first proposes a circuit compensation scheme for the difference in resistance values of SOT devices, which solves this variability problem at the circuit level. Moreover, a synergistic scheme with the circuit is developed based on the correspondence between the multistate resistance characteristics of the SOT devices and a convolutional algorithm. To achieve this, a multichannel SOT convolutional kernel circuit architecture is built, which implements an image edge recognition application. Finally, based on a simulation model, an image edge recognition hardware circuit based on our CoPt-SOT devices is implemented, which is capable of performing image edge recognition with an accuracy of 96.33%. This scheme provides technical support and development prospects for SOT devices in neural network hardware applications.</description><identifier>ISSN: 0003-6951</identifier><identifier>EISSN: 1077-3118</identifier><identifier>DOI: 10.1063/5.0220711</identifier><identifier>CODEN: APPLAB</identifier><language>eng</language><publisher>Melville: American Institute of Physics</publisher><subject>Algorithms ; Devices ; Hardware ; Neural networks ; Neuromorphic computing ; Torque</subject><ispartof>Applied physics letters, 2024-09, Vol.125 (10)</ispartof><rights>Author(s)</rights><rights>2024 Author(s). Published under an exclusive license by AIP Publishing.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c182t-3f2bd5253b37d46b454296edbb3b780e6223cba0cc6e706b4fb3ecf6916961373</cites><orcidid>0000-0001-9017-4896 ; 0000-0001-8999-562X ; 0000-0003-0774-788X ; 0000-0001-6335-2095 ; 0000-0002-3326-4251</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://pubs.aip.org/apl/article-lookup/doi/10.1063/5.0220711$$EHTML$$P50$$Gscitation$$H</linktohtml><link.rule.ids>314,780,784,794,4512,27924,27925,76256</link.rule.ids></links><search><creatorcontrib>Yang, Liu</creatorcontrib><creatorcontrib>Li, Wendi</creatorcontrib><creatorcontrib>Zuo, Chao</creatorcontrib><creatorcontrib>Tao, Ying</creatorcontrib><creatorcontrib>Jin, Fang</creatorcontrib><creatorcontrib>Li, Huihui</creatorcontrib><creatorcontrib>Tang, RuJun</creatorcontrib><creatorcontrib>Dong, Kaifeng</creatorcontrib><title>Field-free multistate spin–orbit torque devices for programmable image edge recognition circuit</title><title>Applied physics letters</title><description>The application of spin–orbit torque (SOT) devices to neuromorphic computing platforms is focused on the development of hardware circuit architectures. However, the inter-device variability, the integration modes of devices and peripheral circuits, and appropriate application scenarios are still unclear, limiting the development of SOT devices in neuromorphic computing. To solve this problem, this paper first proposes a circuit compensation scheme for the difference in resistance values of SOT devices, which solves this variability problem at the circuit level. Moreover, a synergistic scheme with the circuit is developed based on the correspondence between the multistate resistance characteristics of the SOT devices and a convolutional algorithm. To achieve this, a multichannel SOT convolutional kernel circuit architecture is built, which implements an image edge recognition application. Finally, based on a simulation model, an image edge recognition hardware circuit based on our CoPt-SOT devices is implemented, which is capable of performing image edge recognition with an accuracy of 96.33%. This scheme provides technical support and development prospects for SOT devices in neural network hardware applications.</description><subject>Algorithms</subject><subject>Devices</subject><subject>Hardware</subject><subject>Neural networks</subject><subject>Neuromorphic computing</subject><subject>Torque</subject><issn>0003-6951</issn><issn>1077-3118</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kMFKAzEQhoMoWKsH3yDgSWFrJtPNdo9SrAoFL3peNtnZkrK7qUlW8OY7-IY-SSPt2csMw3zM_P_P2DWIGQiF9_lMSCkKgBM2AVEUGQIsTtlECIGZKnM4ZxchbNOYS8QJq1eWuiZrPRHvxy7aEOtIPOzs8Pv947y2kUfnP0biDX1aQ4G3zvOddxtf932tO-K2rzfEqUnFk3GbwUbrBm6sN6ONl-ysrbtAV8c-Ze-rx7flc7Z-fXpZPqwzAwsZM2ylbnKZo8aimSs9z-eyVNRojbpYCFJSotG1MEZRIdK-1UimVSWoUgEWOGU3h7tJW5IbYrV1ox_SywohuYcSsEzU7YEy3oXgqa12Pun3XxWI6i_BKq-OCSb27sAGY1MqydM_8B694XHf</recordid><startdate>20240902</startdate><enddate>20240902</enddate><creator>Yang, Liu</creator><creator>Li, Wendi</creator><creator>Zuo, Chao</creator><creator>Tao, Ying</creator><creator>Jin, Fang</creator><creator>Li, Huihui</creator><creator>Tang, RuJun</creator><creator>Dong, Kaifeng</creator><general>American Institute of Physics</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0001-9017-4896</orcidid><orcidid>https://orcid.org/0000-0001-8999-562X</orcidid><orcidid>https://orcid.org/0000-0003-0774-788X</orcidid><orcidid>https://orcid.org/0000-0001-6335-2095</orcidid><orcidid>https://orcid.org/0000-0002-3326-4251</orcidid></search><sort><creationdate>20240902</creationdate><title>Field-free multistate spin–orbit torque devices for programmable image edge recognition circuit</title><author>Yang, Liu ; Li, Wendi ; Zuo, Chao ; Tao, Ying ; Jin, Fang ; Li, Huihui ; Tang, RuJun ; Dong, Kaifeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c182t-3f2bd5253b37d46b454296edbb3b780e6223cba0cc6e706b4fb3ecf6916961373</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Devices</topic><topic>Hardware</topic><topic>Neural networks</topic><topic>Neuromorphic computing</topic><topic>Torque</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yang, Liu</creatorcontrib><creatorcontrib>Li, Wendi</creatorcontrib><creatorcontrib>Zuo, Chao</creatorcontrib><creatorcontrib>Tao, Ying</creatorcontrib><creatorcontrib>Jin, Fang</creatorcontrib><creatorcontrib>Li, Huihui</creatorcontrib><creatorcontrib>Tang, RuJun</creatorcontrib><creatorcontrib>Dong, Kaifeng</creatorcontrib><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Applied physics letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yang, Liu</au><au>Li, Wendi</au><au>Zuo, Chao</au><au>Tao, Ying</au><au>Jin, Fang</au><au>Li, Huihui</au><au>Tang, RuJun</au><au>Dong, Kaifeng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Field-free multistate spin–orbit torque devices for programmable image edge recognition circuit</atitle><jtitle>Applied physics letters</jtitle><date>2024-09-02</date><risdate>2024</risdate><volume>125</volume><issue>10</issue><issn>0003-6951</issn><eissn>1077-3118</eissn><coden>APPLAB</coden><abstract>The application of spin–orbit torque (SOT) devices to neuromorphic computing platforms is focused on the development of hardware circuit architectures. However, the inter-device variability, the integration modes of devices and peripheral circuits, and appropriate application scenarios are still unclear, limiting the development of SOT devices in neuromorphic computing. To solve this problem, this paper first proposes a circuit compensation scheme for the difference in resistance values of SOT devices, which solves this variability problem at the circuit level. Moreover, a synergistic scheme with the circuit is developed based on the correspondence between the multistate resistance characteristics of the SOT devices and a convolutional algorithm. To achieve this, a multichannel SOT convolutional kernel circuit architecture is built, which implements an image edge recognition application. Finally, based on a simulation model, an image edge recognition hardware circuit based on our CoPt-SOT devices is implemented, which is capable of performing image edge recognition with an accuracy of 96.33%. This scheme provides technical support and development prospects for SOT devices in neural network hardware applications.</abstract><cop>Melville</cop><pub>American Institute of Physics</pub><doi>10.1063/5.0220711</doi><tpages>6</tpages><orcidid>https://orcid.org/0000-0001-9017-4896</orcidid><orcidid>https://orcid.org/0000-0001-8999-562X</orcidid><orcidid>https://orcid.org/0000-0003-0774-788X</orcidid><orcidid>https://orcid.org/0000-0001-6335-2095</orcidid><orcidid>https://orcid.org/0000-0002-3326-4251</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0003-6951
ispartof Applied physics letters, 2024-09, Vol.125 (10)
issn 0003-6951
1077-3118
language eng
recordid cdi_crossref_primary_10_1063_5_0220711
source AIP Journals Complete
subjects Algorithms
Devices
Hardware
Neural networks
Neuromorphic computing
Torque
title Field-free multistate spin–orbit torque devices for programmable image edge recognition circuit
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T05%3A11%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Field-free%20multistate%20spin%E2%80%93orbit%20torque%20devices%20for%20programmable%20image%20edge%20recognition%20circuit&rft.jtitle=Applied%20physics%20letters&rft.au=Yang,%20Liu&rft.date=2024-09-02&rft.volume=125&rft.issue=10&rft.issn=0003-6951&rft.eissn=1077-3118&rft.coden=APPLAB&rft_id=info:doi/10.1063/5.0220711&rft_dat=%3Cproquest_cross%3E3100319139%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3100319139&rft_id=info:pmid/&rfr_iscdi=true