{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T06:10:04Z","timestamp":1767852604682,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3676536.3676740","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T13:21:20Z","timestamp":1744204880000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Power Co-Optimization and Management for LLM Chiplet Designs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5321-8297","authenticated-orcid":false,"given":"Yanchi","family":"Dong","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8906-6189","authenticated-orcid":false,"given":"Xueping","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2127-6011","authenticated-orcid":false,"given":"Xiaochen","family":"Hao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9076-7998","authenticated-orcid":false,"given":"Yun","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8146-4821","authenticated-orcid":false,"given":"Ru","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0599-7762","authenticated-orcid":false,"given":"Le","family":"Ye","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4570-4613","authenticated-orcid":false,"given":"Tianyu","family":"Jia","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"57","volume-title":"Pioneering chiplet technology and design for the amd epyc\u2122 and ryzen\u2122 processor families : Industrial product,\" in ACM\/IEEE International Symposium on Computer Architecture (ISCA)","author":"Naffziger S.","year":"2021","unstructured":"S. Naffziger et al., \"Pioneering chiplet technology and design for the amd epyc\u2122 and ryzen\u2122 processor families : Industrial product,\" in ACM\/IEEE International Symposium on Computer Architecture (ISCA), pp. 57--70, 2021."},{"key":"e_1_3_2_1_2_1","volume-title":"Ponte vecchio: A multi-tile 3d stacked processor for exascale computing,\" in IEEE International Solid-State Circuits Conference (ISSCC)","author":"Gomes W.","year":"2022","unstructured":"W. Gomes et al., \"Ponte vecchio: A multi-tile 3d stacked processor for exascale computing,\" in IEEE International Solid-State Circuits Conference (ISSCC), 2022."},{"issue":"12","key":"e_1_3_2_1_3_1","first-page":"2148","article-title":"Chiplet\/interposer co-design for power delivery network optimization in heterogeneous 2.5-d ics","volume":"11","author":"Kim J.","year":"2021","unstructured":"J. Kim et al., \"Chiplet\/interposer co-design for power delivery network optimization in heterogeneous 2.5-d ics,\" IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 11, no. 12, pp. 2148--2157, 2021.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3176219"},{"key":"e_1_3_2_1_5_1","volume-title":"Flexgen: High-throughput generative inference of large language models with a single GPU,\" in International Conference on Machine Learning","author":"Sheng Y.","year":"2023","unstructured":"Y. Sheng et al., \"Flexgen: High-throughput generative inference of large language models with a single GPU,\" in International Conference on Machine Learning, 2023."},{"key":"e_1_3_2_1_6_1","volume-title":"Fact: Ffn-attention co-optimized transformer architecture with eager correlation prediction,\" in ACM\/IEEE International Symposium on Computer Architecture (ISCA)","author":"Qin Y.","year":"2023","unstructured":"Y. Qin et al., \"Fact: Ffn-attention co-optimized transformer architecture with eager correlation prediction,\" in ACM\/IEEE International Symposium on Computer Architecture (ISCA), 2023."},{"key":"e_1_3_2_1_7_1","volume-title":"Edgemoe: Fast on-device inference of moe-based large language models,\" arXiv preprint arXiv:2308.14352","author":"Yi R.","year":"2023","unstructured":"R. Yi et al., \"Edgemoe: Fast on-device inference of moe-based large language models,\" arXiv preprint arXiv:2308.14352, 2023."},{"key":"e_1_3_2_1_8_1","first-page":"164","volume-title":"Power management for chiplet-based multicore systems using deep reinforcement learning,\" in IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","author":"Li X.","year":"2022","unstructured":"X. Li et al., \"Power management for chiplet-based multicore systems using deep reinforcement learning,\" in IEEE Computer Society Annual Symposium on VLSI (ISVLSI), pp. 164--169, 2022."},{"key":"e_1_3_2_1_9_1","volume-title":"Simba: Scaling deep-learning inference with multi-chip-module-based architecture,\" in International Symp. on Microarchitecture (MICRO)","author":"Shao Y. S.","year":"2019","unstructured":"Y. S. Shao et al., \"Simba: Scaling deep-learning inference with multi-chip-module-based architecture,\" in International Symp. on Microarchitecture (MICRO), 2019."},{"key":"e_1_3_2_1_10_1","first-page":"1013","volume-title":"Nn-baton: Dnn workload orchestration and chiplet granularity exploration for multichip accelerators,\" in ACM\/IEEE International Symposium on Computer Architecture (ISCA)","author":"Tan Z.","year":"2021","unstructured":"Z. Tan et al., \"Nn-baton: Dnn workload orchestration and chiplet granularity exploration for multichip accelerators,\" in ACM\/IEEE International Symposium on Computer Architecture (ISCA), pp. 1013--1026, 2021."},{"key":"e_1_3_2_1_11_1","volume-title":"25.1 A fully synthesizable distributed and scalable all-digital ldo in 10nm cmos,\" in International Solid-State Circuits Conference (ISSCC)","author":"Bang S.","year":"2020","unstructured":"S. Bang et al., \"25.1 A fully synthesizable distributed and scalable all-digital ldo in 10nm cmos,\" in International Solid-State Circuits Conference (ISSCC), 2020."},{"key":"e_1_3_2_1_12_1","unstructured":"Online in https:\/\/www.ferric.com\/products."},{"key":"e_1_3_2_1_13_1","unstructured":"Online in https:\/\/www.ti.com\/document-viewer\/tps546d24s\/datasheet."},{"key":"e_1_3_2_1_14_1","volume-title":"ICML'23","author":"Leviathan Y.","year":"2023","unstructured":"Y. Leviathan et al., \"Fast inference from transformers via speculative decoding,\" in Proceedings of the 40th International Conference on Machine Learning, ICML'23, 2023."},{"key":"e_1_3_2_1_15_1","volume-title":"Language models are few-shot learners,\" in International Conference on Neural Information Processing Systems (NIPS)","author":"Brown T. B.","year":"2020","unstructured":"T. B. Brown et al., \"Language models are few-shot learners,\" in International Conference on Neural Information Processing Systems (NIPS), 2020."},{"key":"e_1_3_2_1_16_1","first-page":"624","volume-title":"Automation and Test in Europe (DATE)","author":"Gupta M. S.","year":"2007","unstructured":"M. S. Gupta et al., \"Understanding voltage variations in chip multiprocessors using a distributed power-delivery network,\" in Conference on Design, Automation and Test in Europe (DATE), p. 624--629, 2007."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2021.3069954"},{"key":"e_1_3_2_1_18_1","volume-title":"Llama: Open and efficient foundation language models,\" arXiv preprint arXiv:2302.13971","author":"Touvron H.","year":"2023","unstructured":"H. Touvron et al., \"Llama: Open and efficient foundation language models,\" arXiv preprint arXiv:2302.13971, 2023."},{"key":"e_1_3_2_1_19_1","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer,\" arXiv preprint arXiv:1910.10683","author":"Raffel C.","year":"2023","unstructured":"C. Raffel et al., \"Exploring the limits of transfer learning with a unified text-to-text transformer,\" arXiv preprint arXiv:1910.10683, 2023."}],"event":{"name":"ICCAD '24: 43rd IEEE\/ACM International Conference on Computer-Aided Design","location":"Newark Liberty International Airport Marriott New York NY USA","acronym":"ICCAD '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE EDS"]},"container-title":["Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676740","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3676740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:43:57Z","timestamp":1750290237000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676740"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":19,"alternative-id":["10.1145\/3676536.3676740","10.1145\/3676536"],"URL":"https:\/\/doi.org\/10.1145\/3676536.3676740","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2025-04-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}