{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:53:01Z","timestamp":1763704381718,"version":"3.45.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"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":[[2025,10,26]]},"DOI":"10.1109\/iccad66269.2025.11240805","type":"proceedings-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:39:34Z","timestamp":1763663974000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Tasa: Thermal-aware 3D-Stacked Architecture Design with Bandwidth Sharing for LLM Inference"],"prefix":"10.1109","author":[{"given":"Siyuan","family":"He","sequence":"first","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Peiran","family":"Yan","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Yandong","family":"He","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Youwei","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]},{"given":"Tianyu","family":"Jia","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}]}],"member":"263","reference":[{"article-title":"Language models are few-shot learners","volume-title":"34th International Conference on Neural Information Processing Systems (NIPS)","author":"Brown","key":"ref1"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651352"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00105"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HCS49909.2020.9220622"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HCS59251.2023.10254711"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2022.3164651"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731694"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/A-SSCC53895.2021.9634704"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00037"},{"article-title":"Ai accelerator hardware trends and research directions","volume-title":"IEDM 2024 Short Course on AI Systems and the Next Leap Forward","author":"Khailany","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM13553.2020.9372039"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185427"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.applthermaleng.2024.123612"},{"key":"ref20","first-page":"365","article-title":"Dark silicon and the end of multicore scaling","volume-title":"2011 38th Annual International Symposium on Computer Architecture (ISCA)","author":"Esmaeilzadeh"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731562"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijheatmasstransfer.2024.126212"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCPMT.2021.3064030"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2927528"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2811411.2811515"},{"key":"ref27","first-page":"648","article-title":"Optimizing energy efficiency of 3-d multicore systems with stacked dram under power and thermal constraints","volume-title":"Design Automation Conference (DAC)","author":"Meng"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3630012"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3677178"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2858230"},{"key":"ref31","article-title":"HotSpot 6.0: Validation, Acceleration and Extension","volume-title":"Tech. Rep. CS-2015-04","author":"Zhang","year":"2015"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942149"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/lca.2023.3333759"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2016.04.006"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC51906.2022.00169"}],"event":{"name":"2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","start":{"date-parts":[[2025,10,26]]},"location":"Munich, Germany","end":{"date-parts":[[2025,10,30]]}},"container-title":["2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11240608\/11240621\/11240805.pdf?arnumber=11240805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:44:36Z","timestamp":1763703876000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240805","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}