High Efficiency Multiply-Accumulator Using Ternary Logic and Ternary Approximate Algorithm

A multiply-accumulator, often abbreviated as a MAC unit, is central to a multitude of computational tasks, particularly those tasks (such as neural networks) involving array-based mathematical computations. The quest for novel methods to efficiently store and process data in a MAC has become imperat...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on circuits and systems. I, Regular papers Jg. 72; H. 7; S. 3258 - 3271
Hauptverfasser:	Wen, Wanting, Zhao, Guangchao, Hu, Wanbo, Li, Ziye, Wang, Xingli, Friedman, Eby G., Tay, Beng Kang, Ke, Shaolin, Huang, Mingqiang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 01.07.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Accumulators Accuracy Adders Algorithms Approximation algorithms Circuits CNTFETs Encoding Field effect transistors multiplying-accumulator Multivalued logic Neural networks Performance evaluation Power management Semiconductor devices Ternary logic circuit Threshold voltage Transistors Vector processing (computers)
ISSN:	1549-8328, 1558-0806
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	A multiply-accumulator, often abbreviated as a MAC unit, is central to a multitude of computational tasks, particularly those tasks (such as neural networks) involving array-based mathematical computations. The quest for novel methods to efficiently store and process data in a MAC has become imperative. Recently, ternary logic has attracted significant attention due to its higher information density than conventional binary systems. However, though numerous studies have showcased ternary arithmetic circuits, advancements in ternary-based vector processing have been notably scarce. To bridge this gap, this work undertakes comprehensive study into the optimization of ternary MAC units. Firstly, we propose various ternary approximate algorithms which shows 30%-less power consumption and only 2% computation error when compared with the accurate design. Secondly, we design sophisticated ternary circuits and obtain 74%~80% lower power-delay-product (PDP) than previous works. Finally, we evaluate the proposed ternary MAC unit using both carbon-nanotube field-effect transistor (CNTFET) and silicon-based 180 nm CMOS processes. The simulation results show the ternary circuit is better than binary circuit in terms of both area (~45% less) and power (~30% less), highlighting its strong potential for practical applications.
AbstractList	A multiply-accumulator, often abbreviated as a MAC unit, is central to a multitude of computational tasks, particularly those tasks (such as neural networks) involving array-based mathematical computations. The quest for novel methods to efficiently store and process data in a MAC has become imperative. Recently, ternary logic has attracted significant attention due to its higher information density than conventional binary systems. However, though numerous studies have showcased ternary arithmetic circuits, advancements in ternary-based vector processing have been notably scarce. To bridge this gap, this work undertakes comprehensive study into the optimization of ternary MAC units. Firstly, we propose various ternary approximate algorithms which shows 30%-less power consumption and only 2% computation error when compared with the accurate design. Secondly, we design sophisticated ternary circuits and obtain 74%~80% lower power-delay-product (PDP) than previous works. Finally, we evaluate the proposed ternary MAC unit using both carbon-nanotube field-effect transistor (CNTFET) and silicon-based 180 nm CMOS processes. The simulation results show the ternary circuit is better than binary circuit in terms of both area (~45% less) and power (~30% less), highlighting its strong potential for practical applications.
Author	Wang, Xingli Tay, Beng Kang Li, Ziye Wen, Wanting Zhao, Guangchao Huang, Mingqiang Friedman, Eby G. Ke, Shaolin Hu, Wanbo
Author_xml	– sequence: 1 givenname: Wanting orcidid: 0009-0009-5683-5019 surname: Wen fullname: Wen, Wanting organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China – sequence: 2 givenname: Guangchao orcidid: 0000-0002-0640-524X surname: Zhao fullname: Zhao, Guangchao organization: Centre for Micro- and Nano-Electronics (CMNE), School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore – sequence: 3 givenname: Wanbo surname: Hu fullname: Hu, Wanbo organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China – sequence: 4 givenname: Ziye surname: Li fullname: Li, Ziye organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China – sequence: 5 givenname: Xingli orcidid: 0000-0003-2411-7804 surname: Wang fullname: Wang, Xingli organization: Centre for Micro- and Nano-Electronics (CMNE), School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore – sequence: 6 givenname: Eby G. orcidid: 0000-0002-5549-7160 surname: Friedman fullname: Friedman, Eby G. organization: Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA – sequence: 7 givenname: Beng Kang orcidid: 0000-0002-3776-3648 surname: Tay fullname: Tay, Beng Kang organization: Centre for Micro- and Nano-Electronics (CMNE), School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore – sequence: 8 givenname: Shaolin orcidid: 0000-0002-4741-8370 surname: Ke fullname: Ke, Shaolin email: keshaolin@wit.edu.cn organization: Hubei Key Laboratory of Optical Information and Pattern Recognition, Wuhan Institute of Technology, Wuhan, China – sequence: 9 givenname: Mingqiang orcidid: 0000-0002-7794-3985 surname: Huang fullname: Huang, Mingqiang email: mq.huang2@siat.ac.cn organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
BookMark	eNpNkE1Lw0AURQepYFv9AYKLgOvU-Uomsyyl2kLFhe3GzTCZj3RKmsSZBMy_N6FFXL3H497H4czApKorA8AjgguEIH_Zrz63CwwxXRDKMePsBkxRkmQxzGA6GXfK44zg7A7MQjhBiDkkaAq-Nq44RmtrnXKmUn303pWta8o-XirVnbtStrWPDsFVRbQ3vpK-j3Z14VQkK_13WTaNr3_cWbYmWpZF7V17PN-DWyvLYB6ucw4Or-v9ahPvPt62q-UuVpimbaw4QZSiXEnNsCZQZwyxnOYwJVYaYzBNmGQklyy3SCONU02JNYZxaak2OZmD58vfgeG7M6EVp7obuMogCMYp5RxTOKTQJaV8HYI3VjR-APa9QFCMCsWoUIwKxVXh0Hm6dNzA8S_PkoQzSH4BBPZwfg
CODEN	ITCSCH
Cites_doi	10.1109/ICEARS53579.2022.9752391 10.3389/fmats.2022.872909 10.1038/s41467-019-09998-x 10.1007/s10470-016-0733-1 10.1109/TETC.2023.3321050 10.1038/s41928-019-0330-2 10.1109/MCSE.2017.29 10.1109/ACCESS.2021.3072567 10.1109/TCSII.2021.3068971 10.1109/TED.2021.3081523 10.1109/ACCESS.2019.2928251 10.1109/TCSI.2017.2686446 10.1109/TCSI.2020.2990748 10.1109/ISMVL.2019.00035 10.1038/nnano.2017.208 10.1038/ncomms13413 10.1109/ISOCC.2017.8368894 10.1016/j.compeleceng.2019.05.018 10.1109/TCSI.2018.2838258 10.1109/TCSII.2022.3210282 10.3390/electronics9040643 10.1109/ACCESS.2020.2997809 10.1016/j.procs.2020.06.073 10.1109/ICECCE49384.2020.9179343 10.1016/j.jmsy.2021.03.005 10.1049/ip-g-2.1990.0005 10.1109/WSCE59557.2023.10366016 10.1109/82.618039
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/TCSI.2024.3492797
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-0806
EndPage	3271
ExternalDocumentID	10_1109_TCSI_2024_3492797 10755970
Genre	orig-research
GrantInformation_xml	– fundername: Natural Science Foundation of Guangdong Province grantid: 2023B1515020051 funderid: 10.13039/501100003453 – fundername: STI 2030, Major Projects grantid: 2022ZD0210600
GroupedDBID	0R~ 29I 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD HZ~ H~9 IFIPE IPLJI JAVBF M43 O9- OCL PZZ RIA RIE RNS VJK AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c246t-c931441bcad72d30d8717b4b063faeee2457a73ba7bf1d1d26d43fee79af4deb3
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001362241500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1549-8328
IngestDate	Sun Oct 26 21:49:38 EDT 2025 Sat Nov 29 07:49:36 EST 2025 Wed Aug 27 02:13:09 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	7
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c246t-c931441bcad72d30d8717b4b063faeee2457a73ba7bf1d1d26d43fee79af4deb3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-3776-3648 0000-0003-2411-7804 0000-0002-4741-8370 0000-0002-7794-3985 0000-0002-5549-7160 0009-0009-5683-5019 0000-0002-0640-524X
PQID	3226499240
PQPubID	85411
PageCount	14
ParticipantIDs	proquest_journals_3226499240 crossref_primary_10_1109_TCSI_2024_3492797 ieee_primary_10755970
PublicationCentury	2000
PublicationDate	2025-07-01
PublicationDateYYYYMMDD	2025-07-01
PublicationDate_xml	– month: 07 year: 2025 text: 2025-07-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on circuits and systems. I, Regular papers
PublicationTitleAbbrev	TCSI
PublicationYear	2025
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref15 Donald (ref5) 1997; 2 ref14 ref30 ref11 ref10 ref2 ref1 ref17 ref16 ref19 ref18 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 ref8 ref7 ref9 ref3 ref6 Weik (ref4) 1961; 45
References_xml	– ident: ref16 doi: 10.1109/ICEARS53579.2022.9752391 – ident: ref11 doi: 10.3389/fmats.2022.872909 – ident: ref10 doi: 10.1038/s41467-019-09998-x – volume: 2 volume-title: The Art of Computer Programming year: 1997 ident: ref5 – ident: ref7 doi: 10.1007/s10470-016-0733-1 – ident: ref22 doi: 10.1109/TETC.2023.3321050 – ident: ref27 doi: 10.1038/s41928-019-0330-2 – ident: ref3 doi: 10.1109/MCSE.2017.29 – ident: ref14 doi: 10.1109/ACCESS.2021.3072567 – ident: ref23 doi: 10.1109/TCSII.2021.3068971 – ident: ref12 doi: 10.1109/TED.2021.3081523 – ident: ref13 doi: 10.1109/ACCESS.2019.2928251 – ident: ref19 doi: 10.1109/TCSI.2017.2686446 – ident: ref26 doi: 10.1109/TCSI.2020.2990748 – ident: ref29 doi: 10.1109/ISMVL.2019.00035 – ident: ref8 doi: 10.1038/nnano.2017.208 – ident: ref9 doi: 10.1038/ncomms13413 – ident: ref24 doi: 10.1109/ISOCC.2017.8368894 – volume: 45 start-page: 571 issue: 244 year: 1961 ident: ref4 article-title: The ENIAC story publication-title: Ordnance – ident: ref15 doi: 10.1016/j.compeleceng.2019.05.018 – ident: ref20 doi: 10.1109/TCSI.2018.2838258 – ident: ref30 doi: 10.1109/TCSII.2022.3210282 – ident: ref28 doi: 10.3390/electronics9040643 – ident: ref25 doi: 10.1109/ACCESS.2020.2997809 – ident: ref1 doi: 10.1016/j.procs.2020.06.073 – ident: ref18 doi: 10.1109/ICECCE49384.2020.9179343 – ident: ref2 doi: 10.1016/j.jmsy.2021.03.005 – ident: ref6 doi: 10.1049/ip-g-2.1990.0005 – ident: ref17 doi: 10.1109/WSCE59557.2023.10366016 – ident: ref21 doi: 10.1109/82.618039
SSID	ssj0029031
Score	2.455564
Snippet	A multiply-accumulator, often abbreviated as a MAC unit, is central to a multitude of computational tasks, particularly those tasks (such as neural networks)...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Index Database Publisher
StartPage	3258
SubjectTerms	Accumulators Accuracy Adders Algorithms Approximation algorithms Circuits CNTFETs Encoding Field effect transistors multiplying-accumulator Multivalued logic Neural networks Performance evaluation Power management Semiconductor devices Ternary logic circuit Threshold voltage Transistors Vector processing (computers)
Title	High Efficiency Multiply-Accumulator Using Ternary Logic and Ternary Approximate Algorithm
URI	https://ieeexplore.ieee.org/document/10755970 https://www.proquest.com/docview/3226499240
Volume	72
WOSCitedRecordID	wos001362241500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-0806 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0029031 issn: 1549-8328 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwGA06POjBnxOnU3LwJGS2Tbo0xzImCjoEJwwvJWlSHWgrXSfuvzdf2o2BePBWSlvavKR5L_m-9yF06WeWhivuk8xqB8KYFkRIxkjoael7Gad97Uxc7_loFE0m4rFJVne5MMYYF3xmenDo9vJ1kc5hqcyOcA4E2Cr0Tc55nay1UlfCo7U5KhPEdtOo2cL0PXE9HjzdWSkYsB548XEweFqbhFxVlV-_Yje_3Oz988320W5DJHFcI3-ANkx-iHbW7AWP0AsEceChM4mADEv8UEcPLkic2idC4a6ixC5oAI9hXbBcYKi9nGKZ69WZGFzHv6eW2Rocv78W5bR6-2ij55vheHBLmloKJA1YvyKpoCCdVCo1DzT1tBVKXDFlGUom7ecELOSSUyW5ynzt66CvGc2M4UJmTFvFfYxaeZGbE4Q1Z8rXlGcq8pmJwiiiEbM8ROggtOCqDrpaNm7yWVtmJE5qeCIBJBJAImmQ6KA2tObahXVDdlB3iUfSjKpZQiHrV1jF6J3-cdsZ2g6gQK-Lp-2iVlXOzTnaSr-q6ay8cB3mB2KJvqQ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwGA0yBfXgz4nTqTl4EjKbJl2a4xgbG25DcMLwUpom1YFu0m3i_nvzpd0YiAdvpbSlzUua95Lvex9CtzS1NFwJSlKrHQjnWhIZc04CT8fUSwWra2fi2hODQTgaycciWd3lwhhjXPCZqcGh28vX02QBS2V2hAsgwFahbwec-zRP11rrK-mx3B6VS2I7alhsYlJP3g-bT10rBn1eAzc-ARZPG9OQq6vy62fsZpj24T_f7QgdFFQSN3Lsj9GWmZyg_Q2DwVP0AmEcuOVsIiDHEvfz-MElaST2iVC6a5phFzaAh7AymC0xVF9OcDzR6zMN8B3_Hltua3Dj_XWajedvH2X03G4Nmx1SVFMgic_rc5JIBuJJJbEWvmaetlJJKK4sR0lj-zk-D0QsmIqFSqmm2q9rzlJjhIxTrq3mPkOlyXRizhHWgiuqmUhVSLkJgzBkIbdMRGo_sPCqCrpbNW70mZtmRE5seDICJCJAIiqQqKAytObGhXlDVlB1hUdUjKtZxCDvV1rN6F38cdsN2u0M-72o1x08XKI9H8r1uujaKirNs4W5QjvJ13w8y65d5_kBd_bB6w
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=High+Efficiency+Multiply-Accumulator+Using+Ternary+Logic+and+Ternary+Approximate+Algorithm&rft.jtitle=IEEE+transactions+on+circuits+and+systems.+I%2C+Regular+papers&rft.au=Wen%2C+Wanting&rft.au=Zhao%2C+Guangchao&rft.au=Hu%2C+Wanbo&rft.au=Li%2C+Ziye&rft.date=2025-07-01&rft.pub=IEEE&rft.issn=1549-8328&rft.volume=72&rft.issue=7&rft.spage=3258&rft.epage=3271&rft_id=info:doi/10.1109%2FTCSI.2024.3492797&rft.externalDocID=10755970
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1549-8328&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1549-8328&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1549-8328&client=summon