{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:12:20Z","timestamp":1775837540652,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-2203399"],"award-info":[{"award-number":["CCF-2203399"]}],"id":[{"id":"10.13039\/100000001","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":[[2023,11]]},"DOI":"10.1109\/tcad.2023.3273992","type":"journal-article","created":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T18:46:17Z","timestamp":1683571577000},"page":"4038-4051","source":"Crossref","is-referenced-by-count":41,"title":["AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference With Transformers"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9230-5877","authenticated-orcid":false,"given":"Shikhar","family":"Tuli","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1539-0369","authenticated-orcid":false,"given":"Niraj K.","family":"Jha","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21236\/ada164453"},{"key":"ref7","first-page":"1218","article-title":"A robustly optimized BERT pre-training approach with post-training","volume-title":"Proc. Chin. Nat. Conf. Comput. Linguist.","author":"Zhuang"},{"key":"ref8","article-title":"Using DeepSpeed and Megatron to train Megatron-turing NLG 530B, a large-scale generative language model","author":"Smith","year":"2022","journal-title":"arXiv:2201.11990"},{"key":"ref9","first-page":"5877","article-title":"The evolved transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"So"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2020.3003328"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01766-7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/hpca47549.2020.00035"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3170848"},{"key":"ref17","first-page":"363","article-title":"OPTIMUS: Optimized matrix multiplication structure for transformer neural network accelerator","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Park"},{"key":"ref18","first-page":"1","article-title":"Incorporating BERT into neural machine translation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00313"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED51717.2021.9424344"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080256"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNANO.2017.2731871"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref26","article-title":"Well-read students learn better: The impact of student initialization on knowledge distillation","author":"Turc","year":"2019","journal-title":"arXiv:1908.08962"},{"key":"ref27","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref28","first-page":"1","article-title":"Bridging nonlinearities and stochastic regularizers with Gaussian error linear units","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"ref30","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Sanh"},{"key":"ref31","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref32","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508431"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IITC.2014.6831837"},{"key":"ref35","volume-title":"Synopsys design compiler","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2018.2832607"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1055137.1055184"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2014.94"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2012.2185930"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2402435"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"issue":"1","key":"ref43","first-page":"37","article-title":"Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation","volume":"2","author":"Powers","year":"2011","journal-title":"J. Mach. Learn. Technol."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42613.2021.9365945"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13942"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586250"},{"key":"ref47","volume-title":"Raspberry Pi 4 model-B","year":"2023"},{"key":"ref48","volume-title":"Intel neural compute stick 2","year":"2023"},{"key":"ref49","volume-title":"Apple unleashes M1","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.vlsi.2017.02.002"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1424"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3575798"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED.2010.5450442"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3389\/felec.2022.847069"},{"key":"ref55","first-page":"1","article-title":"A fast post-training pruning framework for transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kwon"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.211"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.11"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00011"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00066"},{"key":"ref62","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sustainlp-1.20"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.829"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3491046"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/43\/10288105\/10120981-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/10288105\/10120981.pdf?arnumber=10120981","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T10:29:59Z","timestamp":1710412199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10120981\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":65,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2023.3273992","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}