Loading…
An Ultra-Dense 2FeFET TCAM Design Based on a Multi-Domain FeFET Model
Ternary content addressable memories (TCAMs) represent a form of logic-in-memory and are currently widely used in routers, caches, and efficient machine learning models. From a technology prospective, researchers have begun to consider various non-volatile (NV) memory technologies to design NV TCAMs...
Saved in:
Published in: | IEEE transactions on circuits and systems. II, Express briefs Express briefs, 2019-09, Vol.66 (9), p.1577-1581 |
---|---|
Main Authors: | , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c344t-c27a4247cfa8c4568f065976042e329ca49476458b4722ef1dbb850fe50e77763 |
---|---|
cites | cdi_FETCH-LOGICAL-c344t-c27a4247cfa8c4568f065976042e329ca49476458b4722ef1dbb850fe50e77763 |
container_end_page | 1581 |
container_issue | 9 |
container_start_page | 1577 |
container_title | IEEE transactions on circuits and systems. II, Express briefs |
container_volume | 66 |
creator | Yin, Xunzhao Ni, Kai Reis, Dayane Datta, Suman Niemier, Michael Hu, Xiaobo Sharon |
description | Ternary content addressable memories (TCAMs) represent a form of logic-in-memory and are currently widely used in routers, caches, and efficient machine learning models. From a technology prospective, researchers have begun to consider various non-volatile (NV) memory technologies to design NV TCAMs that may offer improvements with respect to figures of merit, such as energy and delay when compared to conventional CMOS designs. Among these devices, ferroelectric field effect transistors (FeFETs) stand out due to their high ION/IOFF ratio, efficient voltage-driven write mechanism, low-cost, and CMOS-compatible fabrication process. We propose a 2FeFET TCAM design based on a state-of-the-art, experimentally calibrated FeFET model. We evaluate and compare our design with other TCAMs at the cell and array levels. Our results suggest that a 2FeFET TCAM requires 3.5×/3200× less write energy than CMOS/resistive random access memory (ReRAM) TCAMs, respectively. The cell area is 13% of that of a CMOS TCAM, and is on par with ReRAM designs. The search energy-delay-product of a 2FeFET TCAM is also 4.1×/2.8× less than CMOS/ReRAM TCAMs, respectively. |
doi_str_mv | 10.1109/TCSII.2018.2889225 |
format | article |
fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_2283374641</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8585162</ieee_id><sourcerecordid>2283374641</sourcerecordid><originalsourceid>FETCH-LOGICAL-c344t-c27a4247cfa8c4568f065976042e329ca49476458b4722ef1dbb850fe50e77763</originalsourceid><addsrcrecordid>eNo9kLFOwzAQhi0EEqXwArBYYk6xz3ZsjyVtIVIrBtrZctMLSpUmxU4H3p6UVEz3S_f9d9JHyCNnE86ZfVlnn3k-AcbNBIyxAOqKjLhSJhHa8utzljbRWupbchfjnjGwTMCIzKcN3dRd8MkMm4gUFriYr-k6m67oDGP11dBXH3FH24Z6ujrVXZXM2oOvGjqQq3aH9T25KX0d8eEyx2TT77L3ZPnxlmfTZVIIKbukAO0lSF2U3hRSpaZkqbI6ZRJQgC28tFKnUpmt1ABY8t12axQrUTHUWqdiTJ6Hu8fQfp8wdm7fnkLTv3QARggtU8l7CgaqCG2MAUt3DNXBhx_HmTvrcn-63FmXu-jqS09DqULE_4JRRvEUxC_Q8mHe</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2283374641</pqid></control><display><type>article</type><title>An Ultra-Dense 2FeFET TCAM Design Based on a Multi-Domain FeFET Model</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Yin, Xunzhao ; Ni, Kai ; Reis, Dayane ; Datta, Suman ; Niemier, Michael ; Hu, Xiaobo Sharon</creator><creatorcontrib>Yin, Xunzhao ; Ni, Kai ; Reis, Dayane ; Datta, Suman ; Niemier, Michael ; Hu, Xiaobo Sharon</creatorcontrib><description>Ternary content addressable memories (TCAMs) represent a form of logic-in-memory and are currently widely used in routers, caches, and efficient machine learning models. From a technology prospective, researchers have begun to consider various non-volatile (NV) memory technologies to design NV TCAMs that may offer improvements with respect to figures of merit, such as energy and delay when compared to conventional CMOS designs. Among these devices, ferroelectric field effect transistors (FeFETs) stand out due to their high ION/IOFF ratio, efficient voltage-driven write mechanism, low-cost, and CMOS-compatible fabrication process. We propose a 2FeFET TCAM design based on a state-of-the-art, experimentally calibrated FeFET model. We evaluate and compare our design with other TCAMs at the cell and array levels. Our results suggest that a 2FeFET TCAM requires 3.5×/3200× less write energy than CMOS/resistive random access memory (ReRAM) TCAMs, respectively. The cell area is 13% of that of a CMOS TCAM, and is on par with ReRAM designs. The search energy-delay-product of a 2FeFET TCAM is also 4.1×/2.8× less than CMOS/ReRAM TCAMs, respectively.</description><identifier>ISSN: 1549-7747</identifier><identifier>EISSN: 1558-3791</identifier><identifier>DOI: 10.1109/TCSII.2018.2889225</identifier><identifier>CODEN: ICSPE5</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Associative memory ; CMOS ; content addressable storage ; Delay ; Delays ; ferroelectric device ; Ferroelectric materials ; Ferroelectricity ; Field effect transistors ; Hysteresis ; Iron ; Logic gates ; Machine learning ; Nonvolatile memory ; Random access memory ; Resistance ; Routers ; Semiconductor device modeling ; Semiconductor devices ; Transistors</subject><ispartof>IEEE transactions on circuits and systems. II, Express briefs, 2019-09, Vol.66 (9), p.1577-1581</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c344t-c27a4247cfa8c4568f065976042e329ca49476458b4722ef1dbb850fe50e77763</citedby><cites>FETCH-LOGICAL-c344t-c27a4247cfa8c4568f065976042e329ca49476458b4722ef1dbb850fe50e77763</cites><orcidid>0000-0002-8571-1308 ; 0000-0002-6636-9738 ; 0000-0003-4656-9545 ; 0000-0002-3628-3431 ; 0000-0001-6044-5173 ; 0000-0001-7776-4306</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8585162$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Yin, Xunzhao</creatorcontrib><creatorcontrib>Ni, Kai</creatorcontrib><creatorcontrib>Reis, Dayane</creatorcontrib><creatorcontrib>Datta, Suman</creatorcontrib><creatorcontrib>Niemier, Michael</creatorcontrib><creatorcontrib>Hu, Xiaobo Sharon</creatorcontrib><title>An Ultra-Dense 2FeFET TCAM Design Based on a Multi-Domain FeFET Model</title><title>IEEE transactions on circuits and systems. II, Express briefs</title><addtitle>TCSII</addtitle><description>Ternary content addressable memories (TCAMs) represent a form of logic-in-memory and are currently widely used in routers, caches, and efficient machine learning models. From a technology prospective, researchers have begun to consider various non-volatile (NV) memory technologies to design NV TCAMs that may offer improvements with respect to figures of merit, such as energy and delay when compared to conventional CMOS designs. Among these devices, ferroelectric field effect transistors (FeFETs) stand out due to their high ION/IOFF ratio, efficient voltage-driven write mechanism, low-cost, and CMOS-compatible fabrication process. We propose a 2FeFET TCAM design based on a state-of-the-art, experimentally calibrated FeFET model. We evaluate and compare our design with other TCAMs at the cell and array levels. Our results suggest that a 2FeFET TCAM requires 3.5×/3200× less write energy than CMOS/resistive random access memory (ReRAM) TCAMs, respectively. The cell area is 13% of that of a CMOS TCAM, and is on par with ReRAM designs. The search energy-delay-product of a 2FeFET TCAM is also 4.1×/2.8× less than CMOS/ReRAM TCAMs, respectively.</description><subject>Associative memory</subject><subject>CMOS</subject><subject>content addressable storage</subject><subject>Delay</subject><subject>Delays</subject><subject>ferroelectric device</subject><subject>Ferroelectric materials</subject><subject>Ferroelectricity</subject><subject>Field effect transistors</subject><subject>Hysteresis</subject><subject>Iron</subject><subject>Logic gates</subject><subject>Machine learning</subject><subject>Nonvolatile memory</subject><subject>Random access memory</subject><subject>Resistance</subject><subject>Routers</subject><subject>Semiconductor device modeling</subject><subject>Semiconductor devices</subject><subject>Transistors</subject><issn>1549-7747</issn><issn>1558-3791</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNo9kLFOwzAQhi0EEqXwArBYYk6xz3ZsjyVtIVIrBtrZctMLSpUmxU4H3p6UVEz3S_f9d9JHyCNnE86ZfVlnn3k-AcbNBIyxAOqKjLhSJhHa8utzljbRWupbchfjnjGwTMCIzKcN3dRd8MkMm4gUFriYr-k6m67oDGP11dBXH3FH24Z6ujrVXZXM2oOvGjqQq3aH9T25KX0d8eEyx2TT77L3ZPnxlmfTZVIIKbukAO0lSF2U3hRSpaZkqbI6ZRJQgC28tFKnUpmt1ABY8t12axQrUTHUWqdiTJ6Hu8fQfp8wdm7fnkLTv3QARggtU8l7CgaqCG2MAUt3DNXBhx_HmTvrcn-63FmXu-jqS09DqULE_4JRRvEUxC_Q8mHe</recordid><startdate>20190901</startdate><enddate>20190901</enddate><creator>Yin, Xunzhao</creator><creator>Ni, Kai</creator><creator>Reis, Dayane</creator><creator>Datta, Suman</creator><creator>Niemier, Michael</creator><creator>Hu, Xiaobo Sharon</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-8571-1308</orcidid><orcidid>https://orcid.org/0000-0002-6636-9738</orcidid><orcidid>https://orcid.org/0000-0003-4656-9545</orcidid><orcidid>https://orcid.org/0000-0002-3628-3431</orcidid><orcidid>https://orcid.org/0000-0001-6044-5173</orcidid><orcidid>https://orcid.org/0000-0001-7776-4306</orcidid></search><sort><creationdate>20190901</creationdate><title>An Ultra-Dense 2FeFET TCAM Design Based on a Multi-Domain FeFET Model</title><author>Yin, Xunzhao ; Ni, Kai ; Reis, Dayane ; Datta, Suman ; Niemier, Michael ; Hu, Xiaobo Sharon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c344t-c27a4247cfa8c4568f065976042e329ca49476458b4722ef1dbb850fe50e77763</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Associative memory</topic><topic>CMOS</topic><topic>content addressable storage</topic><topic>Delay</topic><topic>Delays</topic><topic>ferroelectric device</topic><topic>Ferroelectric materials</topic><topic>Ferroelectricity</topic><topic>Field effect transistors</topic><topic>Hysteresis</topic><topic>Iron</topic><topic>Logic gates</topic><topic>Machine learning</topic><topic>Nonvolatile memory</topic><topic>Random access memory</topic><topic>Resistance</topic><topic>Routers</topic><topic>Semiconductor device modeling</topic><topic>Semiconductor devices</topic><topic>Transistors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yin, Xunzhao</creatorcontrib><creatorcontrib>Ni, Kai</creatorcontrib><creatorcontrib>Reis, Dayane</creatorcontrib><creatorcontrib>Datta, Suman</creatorcontrib><creatorcontrib>Niemier, Michael</creatorcontrib><creatorcontrib>Hu, Xiaobo Sharon</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library Online</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on circuits and systems. II, Express briefs</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yin, Xunzhao</au><au>Ni, Kai</au><au>Reis, Dayane</au><au>Datta, Suman</au><au>Niemier, Michael</au><au>Hu, Xiaobo Sharon</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An Ultra-Dense 2FeFET TCAM Design Based on a Multi-Domain FeFET Model</atitle><jtitle>IEEE transactions on circuits and systems. II, Express briefs</jtitle><stitle>TCSII</stitle><date>2019-09-01</date><risdate>2019</risdate><volume>66</volume><issue>9</issue><spage>1577</spage><epage>1581</epage><pages>1577-1581</pages><issn>1549-7747</issn><eissn>1558-3791</eissn><coden>ICSPE5</coden><abstract>Ternary content addressable memories (TCAMs) represent a form of logic-in-memory and are currently widely used in routers, caches, and efficient machine learning models. From a technology prospective, researchers have begun to consider various non-volatile (NV) memory technologies to design NV TCAMs that may offer improvements with respect to figures of merit, such as energy and delay when compared to conventional CMOS designs. Among these devices, ferroelectric field effect transistors (FeFETs) stand out due to their high ION/IOFF ratio, efficient voltage-driven write mechanism, low-cost, and CMOS-compatible fabrication process. We propose a 2FeFET TCAM design based on a state-of-the-art, experimentally calibrated FeFET model. We evaluate and compare our design with other TCAMs at the cell and array levels. Our results suggest that a 2FeFET TCAM requires 3.5×/3200× less write energy than CMOS/resistive random access memory (ReRAM) TCAMs, respectively. The cell area is 13% of that of a CMOS TCAM, and is on par with ReRAM designs. The search energy-delay-product of a 2FeFET TCAM is also 4.1×/2.8× less than CMOS/ReRAM TCAMs, respectively.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TCSII.2018.2889225</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0002-8571-1308</orcidid><orcidid>https://orcid.org/0000-0002-6636-9738</orcidid><orcidid>https://orcid.org/0000-0003-4656-9545</orcidid><orcidid>https://orcid.org/0000-0002-3628-3431</orcidid><orcidid>https://orcid.org/0000-0001-6044-5173</orcidid><orcidid>https://orcid.org/0000-0001-7776-4306</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1549-7747 |
ispartof | IEEE transactions on circuits and systems. II, Express briefs, 2019-09, Vol.66 (9), p.1577-1581 |
issn | 1549-7747 1558-3791 |
language | eng |
recordid | cdi_proquest_journals_2283374641 |
source | IEEE Electronic Library (IEL) Journals |
subjects | Associative memory CMOS content addressable storage Delay Delays ferroelectric device Ferroelectric materials Ferroelectricity Field effect transistors Hysteresis Iron Logic gates Machine learning Nonvolatile memory Random access memory Resistance Routers Semiconductor device modeling Semiconductor devices Transistors |
title | An Ultra-Dense 2FeFET TCAM Design Based on a Multi-Domain FeFET Model |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T23%3A50%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20Ultra-Dense%202FeFET%20TCAM%20Design%20Based%20on%20a%20Multi-Domain%20FeFET%20Model&rft.jtitle=IEEE%20transactions%20on%20circuits%20and%20systems.%20II,%20Express%20briefs&rft.au=Yin,%20Xunzhao&rft.date=2019-09-01&rft.volume=66&rft.issue=9&rft.spage=1577&rft.epage=1581&rft.pages=1577-1581&rft.issn=1549-7747&rft.eissn=1558-3791&rft.coden=ICSPE5&rft_id=info:doi/10.1109/TCSII.2018.2889225&rft_dat=%3Cproquest_ieee_%3E2283374641%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c344t-c27a4247cfa8c4568f065976042e329ca49476458b4722ef1dbb850fe50e77763%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2283374641&rft_id=info:pmid/&rft_ieee_id=8585162&rfr_iscdi=true |