{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T21:14:34Z","timestamp":1774127674630,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"Anhui Postdoctoral Scientific Research Program Foundation","doi-asserted-by":"publisher","award":["2024A776"],"award-info":[{"award-number":["2024A776"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92473114"],"award-info":[{"award-number":["92473114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2023-003"],"award-info":[{"award-number":["GXXT-2023-003"]}]},{"name":"Strategic Priority Research Program of the CAS","award":["XDB0660000"],"award-info":[{"award-number":["XDB0660000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tcad.2025.3574235","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T13:18:20Z","timestamp":1748351900000},"page":"120-133","source":"Crossref","is-referenced-by-count":2,"title":["Throughput Maximization for Transformer Inference on Processing Near-Memory Architectures"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7888-9370","authenticated-orcid":false,"given":"Mengke","family":"Ge","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]},{"given":"Yingjian","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0341-3428","authenticated-orcid":false,"given":"Song","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5487-6855","authenticated-orcid":false,"given":"Yi","family":"Kang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref4","article-title":"Text embeddings by weakly-supervised contrastive pre-training","author":"Wang","year":"2024","journal-title":"arXiv:2212.03533"},{"key":"ref5","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474146"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582026"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185427"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037702"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731694"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3659951"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895630"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.41"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895534"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3342605"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586212"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3483633"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00050"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623797"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589048"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3125949"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LCN52139.2021.9524928"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3084509"},{"key":"ref38","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2020.3022920"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3576196"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref43","volume-title":"NVDLA deep learning accelerator","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3123178"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2023.3253686"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM13553.2020.9372039"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00065"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00058"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3500360"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/mdat.2025.3527371"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"ref53","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Sheng"},{"key":"ref54","volume-title":"Gurobi optimizer reference manual","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731686"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2021.3061905"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557149"},{"key":"ref59","first-page":"5506","article-title":"i-BERT: Integer-only BERT quantization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Kim"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/164"},{"key":"ref61","first-page":"1","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"He"},{"key":"ref62","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2020","journal-title":"arXiv:1909.11942"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3443718"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/11329484\/11016061.pdf?arnumber=11016061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T05:52:02Z","timestamp":1767765122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11016061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":63,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2025.3574235","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}