{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:13:51Z","timestamp":1781622831544,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/USG.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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. Emerg. Topics Comput."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tetc.2025.3574508","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T13:37:44Z","timestamp":1749130664000},"page":"1215-1229","source":"Crossref","is-referenced-by-count":2,"title":["What, When, Where to Compute-in-Memory for Efficient Matrix Multiplication During Machine Learning Inference"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8307-5785","authenticated-orcid":false,"given":"Tanvi","family":"Sharma","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4452-6464","authenticated-orcid":false,"given":"Mustafa","family":"Ali","sequence":"additional","affiliation":[{"name":"Azure Hardware Systems & Infrastructure, Microsoft, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4829-3706","authenticated-orcid":false,"given":"Indranil","family":"Chakraborty","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0735-9695","authenticated-orcid":false,"given":"Kaushik","family":"Roy","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2018.8614482"},{"key":"ref2","article-title":"Full stack optimization of transformer inference: A survey","author":"Kim","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/216585.216588"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2019.2922889"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10248014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-7487-7_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3082003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322257"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00068"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378497"},{"key":"ref11","article-title":"Ampere Architecture"},{"key":"ref12","volume-title":"Linear Algebraic Primitives for Parallel Computing on Large Graphs","author":"Buluc","year":"2010"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2939682"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2021.3073254"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CICC57935.2023.10121243"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365766"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067555"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731681"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731754"},{"key":"ref20","article-title":"cuDNN: Efficient primitives for deep learning","author":"Chetlur","year":"2014"},{"key":"ref21","article-title":"Matrix multiplication background user\u2019s guide","author":"Docs","year":"2020-2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527431"},{"key":"ref23","article-title":"Benchmarking and modeling of analog and digital sram in-memory computing architectures","author":"Houshmand","year":"2023"},{"key":"ref24","article-title":"Deep learning recommendation model for personalization and recommendation systems","author":"Naumov","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080254"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2985963"},{"key":"ref28","article-title":"Zigzag: A memory-centric rapid DNN accelerator design space exploration framework","author":"Mei","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/OJSSCS.2022.3210152"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LSSC.2021.3092727"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304049"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062985"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2020.2981901"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.vlsi.2017.02.002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"ref37","article-title":"LLM. int8\u2013bit matrix multiplication for transformers at scale","author":"Dettmers","year":"2022"},{"key":"ref38","first-page":"1","article-title":"Accelergy: An architecture-level energy estimation methodology for accelerator designs","volume-title":"Proc. IEEE\/ACM Int. Conf. Comput. Aided Des.","author":"Yannan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref41","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref42","article-title":"GPT-J-6B: A 6 billion parameter autoregressive language model","author":"Wang","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774573"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067527"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42615.2023.10067779"}],"container-title":["IEEE Transactions on Emerging Topics in Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6245516\/11159571\/11026257.pdf?arnumber=11026257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T17:31:17Z","timestamp":1757698277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11026257\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tetc.2025.3574508","relation":{},"ISSN":["2168-6750","2376-4562"],"issn-type":[{"value":"2168-6750","type":"electronic"},{"value":"2376-4562","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}