{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T20:33:09Z","timestamp":1774729989963,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["CNS-2216746"],"award-info":[{"award-number":["CNS-2216746"]}],"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":[[2023,12]]},"DOI":"10.1109\/tcad.2023.3283443","type":"journal-article","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T02:47:05Z","timestamp":1686106025000},"page":"4817-4830","source":"Crossref","is-referenced-by-count":7,"title":["TransCODE: Co-Design of Transformers and Accelerators for Efficient Training and Inference"],"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","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":"ref3","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636301"},{"key":"ref7","first-page":"1","article-title":"Proof artifact co-training for theorem proving with language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Han"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01896"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.03.012"},{"key":"ref10","volume-title":"Raspberry Pi 4 model-B.","year":"2022"},{"key":"ref11","article-title":"EdgeTran: Co-designing transformers for efficient inference on mobile edge platforms","author":"Tuli","year":"2023","journal-title":"arXiv:2303.13745"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/hpca47549.2020.00035"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3170848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3273992"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13942"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3575798"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586250"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643586"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530585"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref24","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":"ref25","first-page":"12837","article-title":"ConvBERT: Improving BERT with span-based dynamic convolution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Jiang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"ref28","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.250"},{"key":"ref30","first-page":"9782","article-title":"DynaBERT: Dynamic BERT with adaptive width and depth","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Hou"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.400"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467262"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218596"},{"key":"ref35","volume-title":"Apple unleashes M1.","year":"2020"},{"key":"ref36","volume-title":"Intel neural compute stick 2.","year":"2023"},{"key":"ref37","volume-title":"NVIDIA Jetson nano developer kit","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3087349"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2020.3003328"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IITC.2014.6831837"},{"key":"ref42","article-title":"Bridging nonlinearities and stochastic regularizers with Gaussian error linear units","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415v2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1201\/9781315220529"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.2307\/2003354"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163351"},{"key":"ref47","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref48","volume-title":"Synopsys design compiler.","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2018.2832607"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1055137.1055184"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2014.94"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2012.2185930"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2402435"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref55","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proc. Int. Conf. Empir. Methods Nat. Lang. Process.","author":"Socher"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref57","first-page":"1","article-title":"Automatically constructing a corpus of sentential paraphrases","volume-title":"Proc. Int. Workshop Paraphrasing","author":"Dolan"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/11736790_9"},{"key":"ref61","first-page":"1","article-title":"The Winograd schema challenge","volume-title":"Proc. Int. Conf. Princ. Knowl. Represent. Reason.","author":"Levesque"},{"key":"ref62","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":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643444"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/43\/10325328\/10144614-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/10325328\/10144614.pdf?arnumber=10144614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T12:56:02Z","timestamp":1710420962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10144614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":66,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2023.3283443","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}