{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:07:35Z","timestamp":1781885255831,"version":"3.54.5"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. VLSI Syst."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/tvlsi.2022.3221390","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T21:14:46Z","timestamp":1669065286000},"page":"114-127","source":"Crossref","is-referenced-by-count":70,"title":["A Heterogeneous and Programmable Compute-In-Memory Accelerator Architecture for Analog-AI Using Dense 2-D Mesh"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2291-7712","authenticated-orcid":false,"given":"Shubham","family":"Jain","sequence":"first","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsinyu","family":"Tsai","sequence":"additional","affiliation":[{"name":"IBM Research–Almaden, San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ching-Tzu","family":"Chen","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3982-3288","authenticated-orcid":false,"given":"Ramachandran","family":"Muralidhar","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4255-8622","authenticated-orcid":false,"given":"Irem","family":"Boybat","sequence":"additional","affiliation":[{"name":"IBM Research Zurich, Rüschlikon, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1545-473X","authenticated-orcid":false,"given":"Martin M.","family":"Frank","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7282-3792","authenticated-orcid":false,"given":"Stanis\u0142aw","family":"Wo\u017aniak","sequence":"additional","affiliation":[{"name":"IBM Research Zurich, Rüschlikon, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milos","family":"Stanisavljevic","sequence":"additional","affiliation":[{"name":"IBM Research Zurich, Rüschlikon, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praneet","family":"Adusumilli","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3176-0059","authenticated-orcid":false,"given":"Pritish","family":"Narayanan","sequence":"additional","affiliation":[{"name":"IBM Research–Almaden, San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kohji","family":"Hosokawa","sequence":"additional","affiliation":[{"name":"IBM Research, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0794-7232","authenticated-orcid":false,"given":"Masatoshi","family":"Ishii","sequence":"additional","affiliation":[{"name":"IBM Research, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arvind","family":"Kumar","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vijay","family":"Narayanan","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5717-2549","authenticated-orcid":false,"given":"Geoffrey W.","family":"Burr","sequence":"additional","affiliation":[{"name":"IBM Research–Almaden, San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"AI and compute","author":"Amodei","year":"2018"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref3","volume-title":"Nvidia Data Center Deep Learning Product Performance","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9063111"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062984"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365791"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365928"},{"key":"ref8","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref9","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2200\/s01004ed1v01y202004cac050"},{"key":"ref12","article-title":"Compute and redundancy solution for Tesla\u2019s full self driving computer","volume-title":"Hot Chips","author":"Sarma","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2021.3063366"},{"key":"ref14","article-title":"Wafer-scale deep learning","volume-title":"Hot Chips","author":"Lie","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6463\/aac8a5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2019.2922889"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41565-020-0655-z"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2021.9641759"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSSC.2019.2936761"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2952773"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3034117"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365788"},{"key":"ref25","article-title":"Analog computation in flash memory for datacenter-scale AI inference in a small chip","volume-title":"Hot Chips","author":"Fick","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2018.8351458"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116401"},{"key":"ref28","volume-title":"The dot-product engine (DPE): Exploring high efficiency analog multiplication with memristor arrays","author":"Strachan","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365769"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CICC51472.2021.9431412"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205297"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2019.8702206"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2014.7047135"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0180-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2021.3115993"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/VLSICircuits52068.2021.9492362"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2017.2716579"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1116\/1.3301579"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2190369"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM19573.2019.8993482"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-16108-9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS51828.2021.9458494"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2018.2796379"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062256"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00753"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.12"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304049"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"ref49","volume-title":"MLPerf Inference Benchmark Suite","year":"2022"},{"key":"ref50","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1465482.1465560"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2021.675741"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref55","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731645"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31405-1"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00073"},{"key":"ref59","first-page":"963","article-title":"Expectation backpropagation: Parameter-free training of multilayer neural networks with continuous or discrete weights","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","volume":"1","author":"Soudry"},{"key":"ref60","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv:1606.06160"},{"key":"ref61","article-title":"Trained ternary quantization","author":"Zhu","year":"2016","journal-title":"arXiv:1612.01064"},{"key":"ref62","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018","journal-title":"arXiv:1805.06085"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2879434"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00070"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.42"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00040"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.32"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783722"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"key":"ref74","article-title":"Ternary neural networks for resource-efficient AI applications","author":"Alemdar","year":"2016","journal-title":"arXiv:1609.00222"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.23919\/FPL.2017.8056823"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00021"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.053631140"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.41"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00015"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.2993045"},{"key":"ref84","first-page":"236","article-title":"Sparse ReRAM engine: Joint exploration of activation and weight sparsity in compressed neural networks","volume-title":"Proc. ACM\/IEEE 46th Annu. Int. Symp. Comput. Archit. (ISCA)","author":"Yang"}],"container-title":["IEEE Transactions on Very Large Scale Integration (VLSI) Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/92\/9998453\/09957094.pdf?arnumber=9957094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:49:45Z","timestamp":1747158585000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9957094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":84,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tvlsi.2022.3221390","relation":{},"ISSN":["1063-8210","1557-9999"],"issn-type":[{"value":"1063-8210","type":"print"},{"value":"1557-9999","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}