{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:14:24Z","timestamp":1780510464987,"version":"3.54.1"},"reference-count":48,"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\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"crossref"}]},{"name":"TxACE"},{"name":"COGNISENSE, one of the seven centers in Joint University Microelectronics Program 2.0 (JUMP 2.0), an SRC Program sponsored by Defense Advanced Research Projects Agency"},{"name":"Intel University FinFET Fabrication Support"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Solid-State Circuits"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/jssc.2025.3603187","type":"journal-article","created":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T17:53:44Z","timestamp":1756922024000},"page":"154-167","source":"Crossref","is-referenced-by-count":2,"title":["T-REX: Hardware\u2013Software Co-Optimized Transformer Accelerator With Reduced External Memory Access and Enhanced Hardware Utilization"],"prefix":"10.1109","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0027-2666","authenticated-orcid":false,"given":"Seunghyun","family":"Moon","sequence":"first","affiliation":[{"name":"Konkuk University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5968-7250","authenticated-orcid":false,"given":"Mao","family":"Li","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4813-3844","authenticated-orcid":false,"given":"Gregory K.","family":"Chen","sequence":"additional","affiliation":[{"name":"Intel Corporation, Hillsboro, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6794-8806","authenticated-orcid":false,"given":"Phil C.","family":"Knag","sequence":"additional","affiliation":[{"name":"Intel Corporation, Hillsboro, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2428-7099","authenticated-orcid":false,"given":"Ram","family":"K. Krishnamurthy","sequence":"additional","affiliation":[{"name":"Intel Corporation, Hillsboro, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9722-0979","authenticated-orcid":false,"given":"Mingoo","family":"Seok","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323725"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247993"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137099"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3315060"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546804"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067842"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185403"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46783.2024.10631541"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185264"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067817"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00079"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00093"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454330"},{"key":"ref16","first-page":"39236","article-title":"Speculative decoding with big little decoder","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref17","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref18","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref19","article-title":"R-drop: Regularized dropout for neural networks","author":"Liang","year":"2021","journal-title":"arXiv:2106.14448"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-demo.6"},{"key":"ref21","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref22","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref23","first-page":"1","article-title":"DictFormer: Tiny transformer with shared dictionary","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lou"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731645"},{"key":"ref25","article-title":"Learning to quantize deep networks by optimizing quantization intervals with task loss","author":"Jung","year":"2018","journal-title":"arXiv:1808.05779"},{"key":"ref26","article-title":"Additive powers-of-two quantization: An efficient non-uniform discretization for neural networks","author":"Li","year":"2019","journal-title":"arXiv:1909.13144"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00499"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2022.3185184"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2871623"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3312615"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CICC60959.2024.10529079"},{"key":"ref32","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref33","article-title":"The era of 1-bit LLMs: All large language models are in 1.58 bits","author":"Ma","year":"2024","journal-title":"arXiv:2402.17764"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.457"},{"key":"ref35","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"arXiv:1905.11946"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070983"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00068"},{"key":"ref38","first-page":"477","article-title":"Stochastic gradient descent training for L1-regularized log-linear models with cumulative penalty","volume-title":"Proc. Joint Conf. 47th Annu. Meeting ACL 4th Int. Joint Conf. Natural Lang. Process.","volume":"1","author":"Tsuruoka"},{"key":"ref39","article-title":"Pruning filters for efficient ConvNets","author":"Li","year":"2016","journal-title":"arXiv:1608.08710"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067615"},{"key":"ref41","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. ICLR","author":"Han"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49661.2025.10904793"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2022.3188428"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731686"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2021.3138520"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2012.6176871"},{"key":"ref48","first-page":"C22","article-title":"A 0.9 pJ\/bit, 12.8 GByte\/s WideIO memory interface in a 3D-IC NoC-based MPSoC","volume-title":"Proc. Symp. VLSI Technol.","author":"Dutoit"}],"container-title":["IEEE Journal of Solid-State Circuits"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4\/11318064\/11148266.pdf?arnumber=11148266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:33:56Z","timestamp":1767076436000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11148266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":48,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jssc.2025.3603187","relation":{},"ISSN":["0018-9200","1558-173X"],"issn-type":[{"value":"0018-9200","type":"print"},{"value":"1558-173X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}