{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:27:39Z","timestamp":1787012859749,"version":"build-2736575974"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62074097"],"award-info":[{"award-number":["62074097"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tcad.2024.3434447","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T15:35:35Z","timestamp":1722267335000},"page":"723-736","source":"Crossref","is-referenced-by-count":9,"title":["COSA Plus: Enhanced Co-Operative Systolic Arrays for Attention Mechanism in Transformers"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6051-9486","authenticated-orcid":false,"given":"Zhican","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6944-2958","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0486-6421","authenticated-orcid":false,"given":"Guanghui","family":"He","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref3","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Dao"},{"key":"ref4","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref9","first-page":"328","article-title":"A3: Accelerating attention mechanisms in neural networks with approximation","volume-title":"Proc. IEEE Int. Symp. High Perform. Comput. Archit. (HPCA)","author":"Ham"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref13","first-page":"1","article-title":"GAMMA: Automating the HW mapping of DNN models on accelerators via genetic algorithm","volume-title":"Proc. 39th Int. Conf. Comput.-Aided Design","author":"Kao"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439477"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MC.1982.1653825"},{"key":"ref17","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019","journal-title":"arXiv:1909.11942"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref25","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref26","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref29","first-page":"1","article-title":"COSA: Co-operative systolic arrays for multi-head attention mechanism in neural network using hybrid data reuse and fusion methodologies","volume-title":"Proc. 60th ACM\/IEEE Design Autom. Conf. (DAC)","author":"Wang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref32","volume-title":"Dive into Deep Learning","author":"Zhang","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3477002"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2022.3196055"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/10848246\/10612833.pdf?arnumber=10612833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T13:54:36Z","timestamp":1737554076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10612833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":34,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2024.3434447","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}