{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T02:26:34Z","timestamp":1783650394785,"version":"3.55.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["2213701"],"award-info":[{"award-number":["2213701"]}]},{"name":"NSF","award":["2217003"],"award-info":[{"award-number":["2217003"]}]},{"name":"NSF","award":["2133267"],"award-info":[{"award-number":["2133267"]}]},{"name":"NSF","award":["2122320"],"award-info":[{"award-number":["2122320"]}]},{"name":"NSF","award":["2324864"],"award-info":[{"award-number":["2324864"]}]},{"name":"NSF","award":["2324937"],"award-info":[{"award-number":["2324937"]}]},{"name":"NSF","award":["2328972"],"award-info":[{"award-number":["2328972"]}]},{"name":"NIH","award":["R01EB033387"],"award-info":[{"award-number":["R01EB033387"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcad.2024.3443692","type":"journal-article","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T18:40:50Z","timestamp":1730918450000},"page":"3949-3960","source":"Crossref","is-referenced-by-count":30,"title":["EQ-ViT: Algorithm-Hardware Co-Design for End-to-End Acceleration of Real-Time Vision Transformer Inference on Versal ACAP Architecture"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5287-5149","authenticated-orcid":false,"given":"Peiyan","family":"Dong","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3659-339X","authenticated-orcid":false,"given":"Jinming","family":"Zhuang","sequence":"additional","affiliation":[{"name":"School of Engineering, Brown University, Providence, RI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7655-4080","authenticated-orcid":false,"given":"Zhuoping","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Engineering, Brown University, Providence, RI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3429-4692","authenticated-orcid":false,"given":"Shixin","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Engineering, Brown University, Providence, RI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1240-4785","authenticated-orcid":false,"given":"Yanyu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1456-9658","authenticated-orcid":false,"given":"Dongkuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3483-8333","authenticated-orcid":false,"given":"Heng","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-4034","authenticated-orcid":false,"given":"Jingtong","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7498-0206","authenticated-orcid":false,"given":"Alex K.","family":"Jones","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6788-9823","authenticated-orcid":false,"given":"Yiyu","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3024-7990","authenticated-orcid":false,"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0493-1844","authenticated-orcid":false,"given":"Peipei","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Engineering, Brown University, Providence, RI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref2","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th ICML","author":"Touvron"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref9","first-page":"1","article-title":"Transformer in transformer","volume-title":"Proc. NeurIPS","author":"Han"},{"key":"ref10","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2021","journal-title":"arXiv:2105.05537"},{"key":"ref11","volume-title":"Autonomous vehicles drive AI advances for edge computing.","author":"Rafie","year":"2021"},{"key":"ref12","volume-title":"Colliding Particles Not Cars: CERN\u2019S Machine Learning Could Help Self-Driving Cars","year":"2023"},{"key":"ref13","article-title":"EdgeRIC: Empowering realtime intelligent optimization and control in nextG networks","author":"Ko","year":"2023","journal-title":"arXiv:2304.11199"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457263"},{"key":"ref15","first-page":"1","article-title":"EfficientFormer: Vision transformers at mobileNet speed","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref16","article-title":"Rethinking vision transformers for mobilenet size and speed","author":"Li","year":"2022","journal-title":"arXiv:2212.08059"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341602"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2011.5763096"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/s19214807"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2017.07.001"},{"key":"ref21","first-page":"1","article-title":"Deep learning inference service at microsoft","volume-title":"Proc. OpML","author":"Soifer"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.42"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.032271057"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1201\/9781003339076-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1063\/5.0001942"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3459009"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071047"},{"key":"ref31","first-page":"1","article-title":"Efficient inference with tensorRT","volume-title":"Proc. GPU Technol. Conf.","volume":"1","author":"Vanholder"},{"key":"ref32","article-title":"Integer quantization for deep learning inference: Principles and empirical evaluation","author":"Wu","year":"2020","journal-title":"arXiv:2004.09602"},{"key":"ref33","volume-title":"Nvidia Nsight systems","year":"2024"},{"key":"ref34","volume-title":"Nvidia TensorRT documentation"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247981"},{"key":"ref36","first-page":"153","article-title":"CHARM: Composing heterogeneous accelerators for matrix multiply on versal ACAP architecture","volume-title":"Proc. FPGA","author":"Zhuang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00065"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197489"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00027"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637569"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref44","article-title":"DETRs beat YOLOs on real-time object detection","author":"Lv","year":"2023","journal-title":"arXiv:2304.08069"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref47","article-title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","author":"Li","year":"2021","journal-title":"arXiv:2102.05426"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref49","first-page":"28089","article-title":"LLM.int8(): 8-bit matrix multiplication for transformers at scale","volume":"33","author":"Dettmers","year":"2021","journal-title":"Proc. NeurIPS"},{"key":"ref50","first-page":"1","article-title":"ZeroQuant: Efficient and affordable post-training quantization for large-scale transformers","volume-title":"Proc. NeurIPS","volume":"35","author":"Yao"},{"key":"ref51","first-page":"28092","article-title":"Q-ViT: Accurate and fully quantized low-bit vision transformer","volume-title":"Proc. NeurIPS","volume":"34","author":"Li"},{"key":"ref52","first-page":"19974","article-title":"Chasing sparsity in vision transformers: An end-to-end exploration","volume-title":"Proc. NeurIPS","volume":"34","author":"Chen"},{"key":"ref53","article-title":"Vision transformer pruning","author":"Zhu","year":"2021","journal-title":"arXiv:2104.08500"},{"key":"ref54","first-page":"1","article-title":"Unified visual transformer compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415609"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2867683"},{"key":"ref58","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3291280.3291800"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/164"},{"key":"ref62","volume-title":"68\u201395\u201399.7 rule","author":"contributors","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-94691-7"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323725"},{"key":"ref65","first-page":"5506","article-title":"I-BERT: Integer-only bert quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref67","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref68","article-title":"All tokens matter: Token labeling for training better vision transformers","author":"Jiang","year":"2021","journal-title":"arXiv:2104.10858"},{"key":"ref69","volume-title":"System management interface SMI | NVIDIA developer"},{"key":"ref70","volume-title":"ViT Github"},{"key":"ref71","volume-title":"Board Evaluation and Management Tool","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00292"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref74","article-title":"Learned step size quantization","author":"Esser","year":"2019","journal-title":"arXiv:1902.08153"},{"key":"ref75","volume-title":"NVIDIA H100 tensor core GPU architecture"},{"key":"ref76","first-page":"881","article-title":"Rammer: Enabling holistic deep learning compiler optimizations with {rTasks}","volume-title":"Proc. OSDI","author":"Ma"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CGO53902.2022.9741270"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/43\/10745760\/10745859-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/10745760\/10745859.pdf?arnumber=10745859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T14:26:25Z","timestamp":1732717585000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10745859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":77,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2024.3443692","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}