001007139 001__ 1007139
001007139 005__ 20230929112527.0
001007139 0247_ $$2doi$$a10.1515/itit-2023-0018
001007139 0247_ $$2ISSN$$a0013-5720
001007139 0247_ $$2ISSN$$a0179-9738
001007139 0247_ $$2ISSN$$a0944-2774
001007139 0247_ $$2ISSN$$a1611-2776
001007139 0247_ $$2ISSN$$a2196-7032
001007139 0247_ $$2Handle$$a2128/34438
001007139 0247_ $$2WOS$$aWOS:000976053800001
001007139 037__ $$aFZJ-2023-01963
001007139 082__ $$a620
001007139 1001_ $$0P:(DE-Juel1)188159$$aBengel, Christopher$$b0
001007139 245__ $$aBit slicing approaches for variability aware ReRAM CIM macros
001007139 260__ $$aBerlin$$b˜Deœ Gruyter$$c2023
001007139 3367_ $$2DRIVER$$aarticle
001007139 3367_ $$2DataCite$$aOutput Types/Journal article
001007139 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1684228149_18883
001007139 3367_ $$2BibTeX$$aARTICLE
001007139 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001007139 3367_ $$00$$2EndNote$$aJournal Article
001007139 520__ $$aComputation-in-Memory accelerators based on resistive switching devices represent a promising approach to realize future information processing systems. These architectures promise orders of magnitudes lower energy consumption for certain tasks, while also achieving higher throughputs than other special purpose hardware such as GPUs, due to their analog computation nature. Due to device variability issues, however, a single resistive switching cell usually does not achieve the resolution required for the considered applications. To overcome this challenge, many of the proposed architectures use an approach called bit slicing, where generally multiple low-resolution components are combined to realize higher resolution blocks. In this paper, we will present an analog accelerator architecture on the circuit level, which can be used to perform Vector-Matrix-Multiplications or Matrix-Matrix-Multiplications. The architecture consists of the 1T1R crossbar array, the optimized select circuitry and an ADC. The components are designed to handle the variability of the resistive switching cells, which is verified through our verified and physical compact model. We then use this architecture to compare different bit slicing approaches and discuss their tradeoffs.
001007139 536__ $$0G:(DE-HGF)POF4-5233$$a5233 - Memristive Materials and Devices (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001007139 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
001007139 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
001007139 536__ $$0G:(GEPRIS)167917811$$aDFG project 167917811 - SFB 917: Resistiv schaltende Chalkogenide für zukünftige Elektronikanwendungen: Struktur, Kinetik und Bauelementskalierung "Nanoswitches" (167917811)$$c167917811$$x3
001007139 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001007139 7001_ $$0P:(DE-HGF)0$$aDixius, Leon$$b1
001007139 7001_ $$0P:(DE-Juel1)131022$$aWaser, R.$$b2$$ufzj
001007139 7001_ $$0P:(DE-HGF)0$$aWouters, Dirk J.$$b3
001007139 7001_ $$0P:(DE-Juel1)158062$$aMenzel, Stephan$$b4$$eCorresponding author
001007139 773__ $$0PERI:(DE-600)2028598-X$$a10.1515/itit-2023-0018$$gVol. 0, no. 0$$n0$$p1$$tInformation technology$$v0$$x0013-5720$$y2023
001007139 8564_ $$uhttps://juser.fz-juelich.de/record/1007139/files/Invoice_APC600410706.pdf
001007139 8564_ $$uhttps://juser.fz-juelich.de/record/1007139/files/Bit-Slicing%20Approaches%20for%20Variability%20Aware%20ReRAM%20CIM%20Macros_final.pdf$$yOpenAccess
001007139 8767_ $$8APC600410706$$92023-04-24$$a1200192894$$d2023-05-09$$eHybrid-OA$$jZahlung erfolgt
001007139 909CO $$ooai:juser.fz-juelich.de:1007139$$pdnbdelivery$$popenCost$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
001007139 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188159$$aForschungszentrum Jülich$$b0$$kFZJ
001007139 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131022$$aForschungszentrum Jülich$$b2$$kFZJ
001007139 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)158062$$aForschungszentrum Jülich$$b4$$kFZJ
001007139 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$$x0
001007139 9141_ $$y2023
001007139 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
001007139 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
001007139 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001007139 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-08-23
001007139 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-08-23
001007139 915__ $$0StatID:(DE-HGF)0112$$2StatID$$aWoS$$bEmerging Sources Citation Index$$d2023-08-23
001007139 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-08-23
001007139 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bIT-INF TECHNOL : 2022$$d2023-08-23
001007139 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2023-08-23
001007139 9201_ $$0I:(DE-Juel1)PGI-7-20110106$$kPGI-7$$lElektronische Materialien$$x0
001007139 9201_ $$0I:(DE-Juel1)PGI-10-20170113$$kPGI-10$$lJARA Institut Green IT$$x1
001007139 9201_ $$0I:(DE-82)080009_20140620$$kJARA-FIT$$lJARA-FIT$$x2
001007139 980__ $$ajournal
001007139 980__ $$aVDB
001007139 980__ $$aUNRESTRICTED
001007139 980__ $$aI:(DE-Juel1)PGI-7-20110106
001007139 980__ $$aI:(DE-Juel1)PGI-10-20170113
001007139 980__ $$aI:(DE-82)080009_20140620
001007139 980__ $$aAPC
001007139 9801_ $$aAPC
001007139 9801_ $$aFullTexts