{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T02:42:18Z","timestamp":1781836938559,"version":"3.54.5"},"reference-count":42,"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\/iccad66269.2025.11240867","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":2,"title":["AccelStack: A Cost-Driven Analysis of 3D-Stacked LLM Accelerators"],"prefix":"10.1109","author":[{"given":"Chen","family":"Bai","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Fan","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"DeepSeek-V3 Technical Report","author":"Liu","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref3","article-title":"OpenAI GPT-5 System Card","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256384"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00068"},{"key":"ref10","article-title":"JEDEC Standard: High Bandwidth Memory (HBM3) DRAM, JEDEC Solid State Technology Association","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC32696.2021.00028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2016.201"},{"key":"ref13","first-page":"22","article-title":"Advanced Packaging Technologies for Heterogeneous Integration","volume-title":"2021 IEEE Hot Chips 27 Symposium (HCS)","author":"Mahajan"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2019.00095"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM50854.2024.10873522"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM50854.2024.10873473"},{"key":"ref17","first-page":"606","article-title":"Efficiently Scaling Transformer Inference","volume":"5","author":"Pope","year":"2023","journal-title":"Machine Learning and Systems (MLSys)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731673"},{"key":"ref19","article-title":"Intel Foveros Direct","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCPMT.2022.3144461"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3085578"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00014"},{"key":"ref23","article-title":"Universal Chiplet Interconnect Express 2.0 Specification","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/74382.74447"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530428"},{"key":"ref26","first-page":"341","article-title":"Reducing Activation Recomputation in Large Transformer Models","volume":"5","author":"Korthikanti","year":"2023","journal-title":"Machine Learning and Systems (MLSys)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731694"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185427"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/215399.215427"},{"key":"ref30","article-title":"NVIDIA GB200 NVL72","year":"2025"},{"key":"ref31","article-title":"Serving Large Language Models on Huawei CloudMatrix384","author":"Zuo","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jik.2024.100482"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2980095"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607102"},{"key":"ref35","article-title":"IC Knowledge LLC. IC Cost and Price Model; Assembly and Test Cost and Price Model","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/ICEP55381.2022.9795476"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC51906.2022.00311"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC51687.2025.00011"},{"key":"ref39","article-title":"Llama: Open and Efficient Foundation Language Models","author":"Touvron","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/DAC63849.2025.11132534"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref42","article-title":"BiE: Bi-Exponent Block Floating-Point for Large Language Models Quantization","volume-title":"International Conference on Machine Learning (ICML)","author":"Zou"}],"event":{"name":"2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","location":"Munich, Germany","start":{"date-parts":[[2025,10,26]]},"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\/11240867.pdf?arnumber=11240867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:45:30Z","timestamp":1763703930000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240867","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}