{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:52:03Z","timestamp":1781589123243,"version":"3.54.5"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Prime Minister\u2019s Office, Singapore, under its Competitive Research Program","doi-asserted-by":"publisher","award":["NRF-CRP24-2020-0002"],"award-info":[{"award-number":["NRF-CRP24-2020-0002"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Prime Minister\u2019s Office, Singapore, under its Competitive Research Program","doi-asserted-by":"publisher","award":["NRF-CRP24-2020-0003"],"award-info":[{"award-number":["NRF-CRP24-2020-0003"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001352","name":"National University of Singapore through the Microelectronics Seed Grant","doi-asserted-by":"publisher","award":["FY2024"],"award-info":[{"award-number":["FY2024"]}],"id":[{"id":"10.13039\/501100001352","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Emerg. Sel. Topics Circuits Syst."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/jetcas.2026.3679018","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T20:07:14Z","timestamp":1774901234000},"page":"378-388","source":"Crossref","is-referenced-by-count":0,"title":["JADE: Joint Architecture-Dataflow Exploration for LLM Inference on Heterogeneous In- and Near-Memory Computing Systems"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7292-0670","authenticated-orcid":false,"given":"Yimin","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4644-0903","authenticated-orcid":false,"given":"Zhen","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7679-4252","authenticated-orcid":false,"given":"Yue Jiet","family":"Chong","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5939-7389","authenticated-orcid":false,"given":"Xuanyao","family":"Fong","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895479"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247873"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323612"},{"key":"ref5","first-page":"1","article-title":"ReTransformer: ReRAM-based processing-in-memory architecture for transformer acceleration","volume-title":"Proc. 39th Int. Conf. Comput.-Aided Design","author":"Yang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213542"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3344524"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2024.3427421"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3649219"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD66269.2025.11240722"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3483633"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2025.3574235"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2025.3566297"},{"key":"ref14","first-page":"257","article-title":"WaferLLM: A wafer-scale LLM inference system","volume-title":"Proc. 19th USENIX Symp. Operating Syst. Design Implement.","author":"He"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3059962"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401746"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401064"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558647"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2022.3171826"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2023.3328864"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558300"},{"key":"ref26","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref27","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref28","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref29","volume-title":"Introducing Llama 3.1: Our Most Capable Models to Date","year":"2024"},{"key":"ref30","volume-title":"Llama 3.2: Revolutionizing Edge AI and Vision With Open, Customizable Models","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875654"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2025.3574508"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2019.2958568"},{"key":"ref37","volume-title":"Bringing HPC Techniques To Deep Learning","author":"Gibiansky","year":"2017"},{"key":"ref38","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018","journal-title":"arXiv:1802.05799"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MSE.2007.44"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.33"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00108"},{"key":"ref43","first-page":"193","article-title":"DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving","volume-title":"Proc. 18th USENIX Symp. Operating Syst. Design Implement.","author":"Zhong"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"}],"container-title":["IEEE Journal on Emerging and Selected Topics in Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5503868\/11563572\/11457955.pdf?arnumber=11457955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:00:27Z","timestamp":1781586027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11457955\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":44,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jetcas.2026.3679018","relation":{},"ISSN":["2156-3357","2156-3365"],"issn-type":[{"value":"2156-3357","type":"print"},{"value":"2156-3365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}