001038334 001__ 1038334
001038334 005__ 20250207215605.0
001038334 0247_ $$2doi$$a10.1038/S41467-024-52488-Y
001038334 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-01332
001038334 0247_ $$2pmid$$a39294142
001038334 0247_ $$2WOS$$aWOS:001315990000007
001038334 037__ $$aFZJ-2025-01332
001038334 082__ $$a500
001038334 1001_ $$0P:(DE-HGF)0$$aBhattacharya, Tinish$$b0$$eCorresponding author
001038334 245__ $$aComputing high-degree polynomial gradients in memory
001038334 260__ $$a[London]$$bSpringer Nature$$c2024
001038334 3367_ $$2DRIVER$$aarticle
001038334 3367_ $$2DataCite$$aOutput Types/Journal article
001038334 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1738911750_16276
001038334 3367_ $$2BibTeX$$aARTICLE
001038334 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001038334 3367_ $$00$$2EndNote$$aJournal Article
001038334 520__ $$aSpecialized function gradient computing hardware could greatly improve the performance of state-of-the-art optimization algorithms. Prior work on such hardware, performed in the context of Ising Machines and related concepts, is limited to quadratic polynomials and not scalable to commonly used higher-order functions. Here, we propose an approach for massively parallel gradient calculations of high-degree polynomials, which is conducive to efficient mixed-signal in-memory computing circuit implementations and whose area scales proportionally with the product of the number of variables and terms in the function and, most importantly, independent of its degree. Two flavors of such an approach are proposed. The first is limited to binary-variable polynomials typical in combinatorial optimization problems, while the second type is broader at the cost of a more complex periphery. To validate the former approach, we experimentally demonstrated solving a small-scale third-order Boolean satisfiability problem based on integrated metal-oxide memristor crossbar circuits, with competitive heuristics algorithm. Simulation results for larger-scale, more practical problems show orders of magnitude improvements in area, speed and energy efficiency compared to the state-of-the-art. We discuss how our work could enable even higher-performance systems after co-designing algorithms to exploit massively parallel gradient computation.
001038334 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001038334 536__ $$0G:(DE-HGF)POF4-5232$$a5232 - Computational Principles (POF4-523)$$cPOF4-523$$fPOF IV$$x1
001038334 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001038334 7001_ $$0P:(DE-HGF)0$$aHutchinson, George H.$$b1
001038334 7001_ $$0P:(DE-HGF)0$$aPedretti, Giacomo$$b2
001038334 7001_ $$0P:(DE-HGF)0$$aSheng, Xia$$b3
001038334 7001_ $$0P:(DE-HGF)0$$aIgnowski, Jim$$b4
001038334 7001_ $$0P:(DE-HGF)0$$aVaerenbergh, Thomas Van$$b5
001038334 7001_ $$0P:(DE-HGF)0$$aBeausoleil, Ray$$b6
001038334 7001_ $$0P:(DE-Juel1)188145$$aStrachan, John Paul$$b7$$ufzj
001038334 7001_ $$0P:(DE-HGF)0$$aStrukov, Dmitri B.$$b8
001038334 773__ $$0PERI:(DE-600)2553671-0$$a10.1038/S41467-024-52488-Y$$gVol. 15, no. 1, p. 8211$$n1$$p8211 (2024)$$tNature Communications$$v15$$x2041-1723$$y2024
001038334 8564_ $$uhttps://juser.fz-juelich.de/record/1038334/files/s41467-024-52488-y.pdf$$yOpenAccess
001038334 909CO $$ooai:juser.fz-juelich.de:1038334$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001038334 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188145$$aForschungszentrum Jülich$$b7$$kFZJ
001038334 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)POF4-5234$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
001038334 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5232$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x1
001038334 9141_ $$y2024
001038334 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001038334 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)9915$$2StatID$$aIF >= 15$$bNAT COMMUN : 2022$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNAT COMMUN : 2022$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-01-30T07:48:07Z
001038334 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-01-30T07:48:07Z
001038334 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-02
001038334 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001038334 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Peer review$$d2024-01-30T07:48:07Z
001038334 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)1060$$2StatID$$aDBCoverage$$bCurrent Contents - Agriculture, Biology and Environmental Sciences$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2025-01-02
001038334 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-02
001038334 9201_ $$0I:(DE-Juel1)PGI-14-20210412$$kPGI-14$$lNeuromorphic Compute Nodes$$x0
001038334 980__ $$ajournal
001038334 980__ $$aVDB
001038334 980__ $$aI:(DE-Juel1)PGI-14-20210412
001038334 980__ $$aUNRESTRICTED
001038334 9801_ $$aFullTexts