{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T13:04:01Z","timestamp":1773320641687,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,19]]},"DOI":"10.1109\/asp-dac66049.2026.11420780","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:51:15Z","timestamp":1773172275000},"page":"162-169","source":"Crossref","is-referenced-by-count":0,"title":["BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Termination"],"prefix":"10.1109","author":[{"given":"Huizheng","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,School of Integrated Circuits,Beijing,China"}]},{"given":"Hongbin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Integrated Circuits,Beijing,China"}]},{"given":"Shaojun","family":"Wei","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Integrated Circuits,Beijing,China"}]},{"given":"Yang","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Integrated Circuits,Beijing,China"}]},{"given":"Shouyi","family":"Yin","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Integrated Circuits,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv preprint arXiv:2206.07682"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511105"},{"key":"ref3","article-title":"Lamda: Language models for dialog applications","author":"Thoppilan","year":"2022","journal-title":"arXiv preprint arXiv:2201.08239"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00632"},{"issue":"8","key":"ref5","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100048"},{"key":"ref7","article-title":"A comprehensive capability analysis of GPT-3 and GPT3.5 series models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv:2303.10420"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3725843.3756037"},{"key":"ref10","article-title":"Full stack optimization of Transformer inference: A survey","author":"Kim","year":"2023","journal-title":"arXiv preprint arXiv:2302.14017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12102299"},{"issue":"2","key":"ref12","article-title":"A survey of large language models","volume":"1","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv:2303.18223"},{"key":"ref13","article-title":"A survey on efficient inference for large language models","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv:2404.14294"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/hpca47549.2020.00035"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3170848"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00093"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527423"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3208206"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3181541"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/micro56248.2022.00050"},{"key":"ref26","first-page":"1","article-title":"Token-picker: Accelerating attention in text generation with minimized memory transfer via probability estimation","volume-title":"Proc. 61st ACM\/IEEE Des. Autom. Conf","author":"Park"},{"key":"ref27","first-page":"1","article-title":"SpARC: Token Similarity-Aware Sparse Attention Transformer Accelerator via Row-wise Clustering","volume-title":"Proc. 61st ACM\/IEEE Des. Autom. Conf. (DAC)","author":"Cho"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2025.3576232"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/isscc.2018.8310262"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00059"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071031"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731043"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655982"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3373592"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070997"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"ref37","article-title":"OPT: Open pre-trained Transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2205.01068"},{"key":"ref38","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref39","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv preprint arXiv:1609.07843"},{"key":"ref40","article-title":"Free dolly: Introducing the world\u2019s first truly open instructiontuned LLM","author":"Conover","year":"2023","journal-title":"Company Blog of Databricks"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3085572"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2023.3333759"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3649476.3658709"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2025.3596228"}],"event":{"name":"2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)","location":"Lantau, Hong Kong","start":{"date-parts":[[2026,1,19]]},"end":{"date-parts":[[2026,1,22]]}},"container-title":["2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11420221\/11420229\/11420780.pdf?arnumber=11420780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T19:36:09Z","timestamp":1773257769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11420780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/asp-dac66049.2026.11420780","relation":{},"subject":[],"published":{"date-parts":[[2026,1,19]]}}}