(Invited) Development, Characterization, and Modeling of a TaOx ReRAM for a Neuromorphic Accelerator

Resistive random access memory (ReRAM), or memristors, may be capable of significantly improving the efficiency of neuromorphic computing, when used as a central component of an analog hardware accelerator. However, the significant electrical variation within a single device and between devices degr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Marinella, Matthew J., Mickel, Patrick R, Lohn, Andrew J, Hughart, David R., Bondi, Robert, Mamaluy, Denis, Hjalmarson, Harold P., Stevens, James E, Decker, Seth, Apodaca, Roger T, Evans, Brian, Aimone, James Bradley, Rothganger, Fred, James, Conrad D., DeBenedictis, Erik P
Format: Tagungsbericht
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 42
container_issue 14
container_start_page 37
container_title
container_volume 64
creator Marinella, Matthew J.
Mickel, Patrick R
Lohn, Andrew J
Hughart, David R.
Bondi, Robert
Mamaluy, Denis
Hjalmarson, Harold P.
Stevens, James E
Decker, Seth
Apodaca, Roger T
Evans, Brian
Aimone, James Bradley
Rothganger, Fred
James, Conrad D.
DeBenedictis, Erik P
description Resistive random access memory (ReRAM), or memristors, may be capable of significantly improving the efficiency of neuromorphic computing, when used as a central component of an analog hardware accelerator. However, the significant electrical variation within a single device and between devices degrades the maximum efficiency and accuracy which can be achieved by a ReRAM-based neuromorphic accelerator. In this report, the electrical variability is characterized, with a particular focus on that which is due to fundamental, intrinsic factors. Analytical and ab initio models are presented which offer insight into the factors responsible for this variability.
doi_str_mv 10.1149/06414.0037ecst
format Conference Proceeding
fullrecord <record><control><sourceid>iop_osti_</sourceid><recordid>TN_cdi_osti_scitechconnect_1241770</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10.1149/06414.0037ecst</sourcerecordid><originalsourceid>FETCH-LOGICAL-i257t-f4b677c6f613bc1a2dab7857526c69d9a610fd0554f121fcddfa66bebb6ec153</originalsourceid><addsrcrecordid>eNo1kM1PAjEQxRujiYhePTee1LDY7m5b9kjwiwQkIdybbjuVkqUl3UKMf72r4GleJu9N5v0QuqVkSGlZPRFe0nJISCFAt-kM9WhVjDIuCnF-0mzE80t01bYbQniXET1k7qf-4BKYB_wMB2jCbgs-DfBkraLSCaL7VskFP8DKGzwPBhrnP3GwWOGVWnzhJSzHc2xD7BYfsI9hG-Ju7TQeaw0NRJVCvEYXVjUt3JxmH61eX1aT92y2eJtOxrPM5UykzJY1F0Jzy2lRa6pyo2oxYoLlXPPKVIpTYg1hrLQ0p1YbYxXnNdQ1B01Z0Ud3x7OhTU62uqul1zp4DzpJmpdUCNKZHo8mF3ZyE_bRdx9JSuQvQ_nHUP4zLH4AsQ5lHw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>(Invited) Development, Characterization, and Modeling of a TaOx ReRAM for a Neuromorphic Accelerator</title><source>Institute of Physics Journals</source><creator>Marinella, Matthew J. ; Mickel, Patrick R ; Lohn, Andrew J ; Hughart, David R. ; Bondi, Robert ; Mamaluy, Denis ; Hjalmarson, Harold P. ; Stevens, James E ; Decker, Seth ; Apodaca, Roger T ; Evans, Brian ; Aimone, James Bradley ; Rothganger, Fred ; James, Conrad D. ; DeBenedictis, Erik P</creator><creatorcontrib>Marinella, Matthew J. ; Mickel, Patrick R ; Lohn, Andrew J ; Hughart, David R. ; Bondi, Robert ; Mamaluy, Denis ; Hjalmarson, Harold P. ; Stevens, James E ; Decker, Seth ; Apodaca, Roger T ; Evans, Brian ; Aimone, James Bradley ; Rothganger, Fred ; James, Conrad D. ; DeBenedictis, Erik P ; Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)</creatorcontrib><description>Resistive random access memory (ReRAM), or memristors, may be capable of significantly improving the efficiency of neuromorphic computing, when used as a central component of an analog hardware accelerator. However, the significant electrical variation within a single device and between devices degrades the maximum efficiency and accuracy which can be achieved by a ReRAM-based neuromorphic accelerator. In this report, the electrical variability is characterized, with a particular focus on that which is due to fundamental, intrinsic factors. Analytical and ab initio models are presented which offer insight into the factors responsible for this variability.</description><identifier>ISSN: 1938-5862</identifier><identifier>ISSN: 1938-6737</identifier><identifier>EISSN: 1938-6737</identifier><identifier>DOI: 10.1149/06414.0037ecst</identifier><language>eng</language><publisher>United States: The Electrochemical Society, Inc</publisher><ispartof>ECS transactions, 2014, Vol.64 (14), p.37-42</ispartof><rights>2014 ECS - The Electrochemical Society</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://iopscience.iop.org/article/10.1149/06414.0037ecst/pdf$$EPDF$$P50$$Giop$$H</linktopdf><link.rule.ids>230,310,315,782,786,791,887,23937,27931,27932,53853,53900</link.rule.ids><backlink>$$Uhttps://www.osti.gov/servlets/purl/1241770$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Marinella, Matthew J.</creatorcontrib><creatorcontrib>Mickel, Patrick R</creatorcontrib><creatorcontrib>Lohn, Andrew J</creatorcontrib><creatorcontrib>Hughart, David R.</creatorcontrib><creatorcontrib>Bondi, Robert</creatorcontrib><creatorcontrib>Mamaluy, Denis</creatorcontrib><creatorcontrib>Hjalmarson, Harold P.</creatorcontrib><creatorcontrib>Stevens, James E</creatorcontrib><creatorcontrib>Decker, Seth</creatorcontrib><creatorcontrib>Apodaca, Roger T</creatorcontrib><creatorcontrib>Evans, Brian</creatorcontrib><creatorcontrib>Aimone, James Bradley</creatorcontrib><creatorcontrib>Rothganger, Fred</creatorcontrib><creatorcontrib>James, Conrad D.</creatorcontrib><creatorcontrib>DeBenedictis, Erik P</creatorcontrib><creatorcontrib>Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)</creatorcontrib><title>(Invited) Development, Characterization, and Modeling of a TaOx ReRAM for a Neuromorphic Accelerator</title><title>ECS transactions</title><addtitle>ECS Trans</addtitle><description>Resistive random access memory (ReRAM), or memristors, may be capable of significantly improving the efficiency of neuromorphic computing, when used as a central component of an analog hardware accelerator. However, the significant electrical variation within a single device and between devices degrades the maximum efficiency and accuracy which can be achieved by a ReRAM-based neuromorphic accelerator. In this report, the electrical variability is characterized, with a particular focus on that which is due to fundamental, intrinsic factors. Analytical and ab initio models are presented which offer insight into the factors responsible for this variability.</description><issn>1938-5862</issn><issn>1938-6737</issn><issn>1938-6737</issn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2014</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNo1kM1PAjEQxRujiYhePTee1LDY7m5b9kjwiwQkIdybbjuVkqUl3UKMf72r4GleJu9N5v0QuqVkSGlZPRFe0nJISCFAt-kM9WhVjDIuCnF-0mzE80t01bYbQniXET1k7qf-4BKYB_wMB2jCbgs-DfBkraLSCaL7VskFP8DKGzwPBhrnP3GwWOGVWnzhJSzHc2xD7BYfsI9hG-Ju7TQeaw0NRJVCvEYXVjUt3JxmH61eX1aT92y2eJtOxrPM5UykzJY1F0Jzy2lRa6pyo2oxYoLlXPPKVIpTYg1hrLQ0p1YbYxXnNdQ1B01Z0Ud3x7OhTU62uqul1zp4DzpJmpdUCNKZHo8mF3ZyE_bRdx9JSuQvQ_nHUP4zLH4AsQ5lHw</recordid><startdate>20140101</startdate><enddate>20140101</enddate><creator>Marinella, Matthew J.</creator><creator>Mickel, Patrick R</creator><creator>Lohn, Andrew J</creator><creator>Hughart, David R.</creator><creator>Bondi, Robert</creator><creator>Mamaluy, Denis</creator><creator>Hjalmarson, Harold P.</creator><creator>Stevens, James E</creator><creator>Decker, Seth</creator><creator>Apodaca, Roger T</creator><creator>Evans, Brian</creator><creator>Aimone, James Bradley</creator><creator>Rothganger, Fred</creator><creator>James, Conrad D.</creator><creator>DeBenedictis, Erik P</creator><general>The Electrochemical Society, Inc</general><scope>OIOZB</scope><scope>OTOTI</scope></search><sort><creationdate>20140101</creationdate><title>(Invited) Development, Characterization, and Modeling of a TaOx ReRAM for a Neuromorphic Accelerator</title><author>Marinella, Matthew J. ; Mickel, Patrick R ; Lohn, Andrew J ; Hughart, David R. ; Bondi, Robert ; Mamaluy, Denis ; Hjalmarson, Harold P. ; Stevens, James E ; Decker, Seth ; Apodaca, Roger T ; Evans, Brian ; Aimone, James Bradley ; Rothganger, Fred ; James, Conrad D. ; DeBenedictis, Erik P</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i257t-f4b677c6f613bc1a2dab7857526c69d9a610fd0554f121fcddfa66bebb6ec153</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2014</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Marinella, Matthew J.</creatorcontrib><creatorcontrib>Mickel, Patrick R</creatorcontrib><creatorcontrib>Lohn, Andrew J</creatorcontrib><creatorcontrib>Hughart, David R.</creatorcontrib><creatorcontrib>Bondi, Robert</creatorcontrib><creatorcontrib>Mamaluy, Denis</creatorcontrib><creatorcontrib>Hjalmarson, Harold P.</creatorcontrib><creatorcontrib>Stevens, James E</creatorcontrib><creatorcontrib>Decker, Seth</creatorcontrib><creatorcontrib>Apodaca, Roger T</creatorcontrib><creatorcontrib>Evans, Brian</creatorcontrib><creatorcontrib>Aimone, James Bradley</creatorcontrib><creatorcontrib>Rothganger, Fred</creatorcontrib><creatorcontrib>James, Conrad D.</creatorcontrib><creatorcontrib>DeBenedictis, Erik P</creatorcontrib><creatorcontrib>Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)</creatorcontrib><collection>OSTI.GOV - Hybrid</collection><collection>OSTI.GOV</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Marinella, Matthew J.</au><au>Mickel, Patrick R</au><au>Lohn, Andrew J</au><au>Hughart, David R.</au><au>Bondi, Robert</au><au>Mamaluy, Denis</au><au>Hjalmarson, Harold P.</au><au>Stevens, James E</au><au>Decker, Seth</au><au>Apodaca, Roger T</au><au>Evans, Brian</au><au>Aimone, James Bradley</au><au>Rothganger, Fred</au><au>James, Conrad D.</au><au>DeBenedictis, Erik P</au><aucorp>Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)</aucorp><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>(Invited) Development, Characterization, and Modeling of a TaOx ReRAM for a Neuromorphic Accelerator</atitle><btitle>ECS transactions</btitle><addtitle>ECS Trans</addtitle><date>2014-01-01</date><risdate>2014</risdate><volume>64</volume><issue>14</issue><spage>37</spage><epage>42</epage><pages>37-42</pages><issn>1938-5862</issn><issn>1938-6737</issn><eissn>1938-6737</eissn><abstract>Resistive random access memory (ReRAM), or memristors, may be capable of significantly improving the efficiency of neuromorphic computing, when used as a central component of an analog hardware accelerator. However, the significant electrical variation within a single device and between devices degrades the maximum efficiency and accuracy which can be achieved by a ReRAM-based neuromorphic accelerator. In this report, the electrical variability is characterized, with a particular focus on that which is due to fundamental, intrinsic factors. Analytical and ab initio models are presented which offer insight into the factors responsible for this variability.</abstract><cop>United States</cop><pub>The Electrochemical Society, Inc</pub><doi>10.1149/06414.0037ecst</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1938-5862
ispartof ECS transactions, 2014, Vol.64 (14), p.37-42
issn 1938-5862
1938-6737
1938-6737
language eng
recordid cdi_osti_scitechconnect_1241770
source Institute of Physics Journals
title (Invited) Development, Characterization, and Modeling of a TaOx ReRAM for a Neuromorphic Accelerator
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-04T20%3A58%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-iop_osti_&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=(Invited)%20Development,%20Characterization,%20and%20Modeling%20of%20a%20TaOx%20ReRAM%20for%20a%20Neuromorphic%20Accelerator&rft.btitle=ECS%20transactions&rft.au=Marinella,%20Matthew%20J.&rft.aucorp=Sandia%20National%20Lab.%20(SNL-NM),%20Albuquerque,%20NM%20(United%20States)&rft.date=2014-01-01&rft.volume=64&rft.issue=14&rft.spage=37&rft.epage=42&rft.pages=37-42&rft.issn=1938-5862&rft.eissn=1938-6737&rft_id=info:doi/10.1149/06414.0037ecst&rft_dat=%3Ciop_osti_%3E10.1149/06414.0037ecst%3C/iop_osti_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true