000912510 001__ 912510
000912510 005__ 20230224084246.0
000912510 0247_ $$2doi$$a10.1109/JXCDC.2022.3217098
000912510 0247_ $$2Handle$$a2128/33019
000912510 0247_ $$2WOS$$aWOS:000915312400008
000912510 037__ $$aFZJ-2022-05683
000912510 082__ $$a530
000912510 1001_ $$00000-0003-3025-8910$$aFreye, Florian$$b0
000912510 245__ $$aMemristive Devices for Time Domain Compute-in-Memory
000912510 260__ $$aNew York, NY$$bIEEE$$c2022
000912510 3367_ $$2DRIVER$$aarticle
000912510 3367_ $$2DataCite$$aOutput Types/Journal article
000912510 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1670913545_31169
000912510 3367_ $$2BibTeX$$aARTICLE
000912510 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000912510 3367_ $$00$$2EndNote$$aJournal Article
000912510 520__ $$aAnalog compute schemes and compute-in-memory (CIM) have emerged in an effort to reduce the increasing power hunger of convolutional neural networks (CNNs), which exceeds the constraints of edge devices. Memristive device types are a relatively new offering with interesting opportunities for unexplored circuit concepts. In this work, the use of memristive devices in cascaded time-domain CIM (TDCIM) is introduced with the primary goal of reducing the size of fully unrolled architectures. The different effects influencing the determinism in memristive devices are outlined together with reliability concerns. Architectures for binary as well as multibit multiply and accumulate (MAC) cells are presented and evaluated. As more involved circuits offer more accurate compute result, a tradeoff between design effort and accuracy comes into the picture. To further evaluate this tradeoff, the impact of variations on overall compute accuracy is discussed. The presented cells reach an energy/OP of 0.23 fJ at a size of 1.2 μm2 for binary and 6.04 fJ at 3.2 μm2 for 4×4 bit MAC operations.
000912510 536__ $$0G:(DE-HGF)POF4-5233$$a5233 - Memristive Materials and Devices (POF4-523)$$cPOF4-523$$fPOF IV$$x0
000912510 536__ $$0G:(DE-82)BMBF-16ME0399$$aBMBF-16ME0399 - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0399)$$cBMBF-16ME0399$$x1
000912510 536__ $$0G:(DE-82)BMBF-16ME0398K$$aBMBF-16ME0398K - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0398K)$$cBMBF-16ME0398K$$x2
000912510 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000912510 7001_ $$00000-0003-0380-8585$$aLou, Jie$$b1
000912510 7001_ $$aBengel, Christopher$$b2
000912510 7001_ $$0P:(DE-Juel1)158062$$aMenzel, Stephan$$b3
000912510 7001_ $$0P:(DE-Juel1)187229$$aWiefels, Stefan$$b4
000912510 7001_ $$00000-0003-1583-3411$$aGemmeke, Tobias$$b5
000912510 773__ $$0PERI:(DE-600)2840841-X$$a10.1109/JXCDC.2022.3217098$$gVol. 8, no. 2, p. 119 - 127$$n2$$p119 - 127$$tIEEE journal on exploratory solid-state computational devices and circuits$$v8$$x2329-9231$$y2022
000912510 8564_ $$uhttps://juser.fz-juelich.de/record/912510/files/Freye2022001.pdf$$yOpenAccess
000912510 909CO $$ooai:juser.fz-juelich.de:912510$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000912510 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)158062$$aForschungszentrum Jülich$$b3$$kFZJ
000912510 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)187229$$aForschungszentrum Jülich$$b4$$kFZJ
000912510 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5233$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
000912510 9141_ $$y2022
000912510 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000912510 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000912510 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2020-08-26
000912510 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2020-08-26
000912510 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-23
000912510 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-01-15T11:05:14Z
000912510 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-01-15T11:05:14Z
000912510 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2021-01-15T11:05:14Z
000912510 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-23
000912510 915__ $$0StatID:(DE-HGF)0112$$2StatID$$aWoS$$bEmerging Sources Citation Index$$d2022-11-23
000912510 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-23
000912510 9201_ $$0I:(DE-Juel1)PGI-7-20110106$$kPGI-7$$lElektronische Materialien$$x0
000912510 9201_ $$0I:(DE-82)080009_20140620$$kJARA-FIT$$lJARA-FIT$$x1
000912510 980__ $$ajournal
000912510 980__ $$aVDB
000912510 980__ $$aI:(DE-Juel1)PGI-7-20110106
000912510 980__ $$aI:(DE-82)080009_20140620
000912510 980__ $$aUNRESTRICTED
000912510 9801_ $$aFullTexts