{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T20:12:33Z","timestamp":1784059953389,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92373103"],"award-info":[{"award-number":["92373103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62204271"],"award-info":[{"award-number":["62204271"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hengqin Guangdong-Macao In-Depth Cooperation Zone Industrial Core and Key Technology Research","award":["2430004045040"],"award-info":[{"award-number":["2430004045040"]}]},{"name":"Opening Project of Key Laboratory of Automotive Chip Testing and Evaluation","award":["QCXP202501"],"award-info":[{"award-number":["QCXP202501"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpds.2026.3704709","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:40:32Z","timestamp":1781725232000},"page":"1981-1996","source":"Crossref","is-referenced-by-count":0,"title":["MAX-SM: High-Utilization Dynamic SM Partitioning for Heterogeneous Workloads on Multitasking Chiplet-Based GPUs"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4006-8870","authenticated-orcid":false,"given":"Mingyu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Microelectronics Science and Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0926-0451","authenticated-orcid":false,"given":"Tao","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Microelectronics Science and Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6674-6163","authenticated-orcid":false,"given":"Peilin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Microelectronics Science and Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baiqing","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Microelectronics Science and Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongchang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaolin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8802-0457","authenticated-orcid":false,"given":"Zhiyi","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Microelectronics Science and Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"ref2","article-title":"NVIDIA A100 Tensor Core GPU architecture","year":"2020"},{"key":"ref3","article-title":"NVIDIA\u2019s next generation CUDA compute architecture: Fermi","year":"2009"},{"key":"ref4","article-title":"Intel delays 10 nm to 2017","year":"2015"},{"key":"ref5","article-title":"International technology roadmap for semiconductors 2.0","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830808"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1145\/3489517.3530428","article-title":"Chiplet actuary: A quantitative cost model and multi-chiplet architecture exploration","volume-title":"Proc. 59th ACM\/IEEE Des. Automat. Conf.","author":"Feng","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ectc32696.2021.00028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2013.2279053"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2875092"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365975"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/isscc.2016.7417967"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080231"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.2018.8502368"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.3023723"},{"key":"ref17","article-title":"Multi-process service","year":"2022"},{"key":"ref18","article-title":"NVIDIA multi-instance GPU user guide","year":"2021"},{"key":"ref19","article-title":"Stream management HIP API","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168946"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818979"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2024.3438549"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3021238"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2313342"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3235439"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.80"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3084804"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3430063"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3548320"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3115630"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2490301.2451160"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037709"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2011.13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2012.6237007"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853208"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694346"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557149"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref41","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"Stratton","year":"2012"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"ref43","article-title":"SDK code samples","year":"2012"},{"key":"ref44","first-page":"260","article-title":"Mars: A MapReduce framework on graphics processors","volume-title":"Proc. Int. Conf. Parallel Architectures Compilation Techn.","author":"He","year":"2008"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205311"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759857"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11558584\/11569358.pdf?arnumber=11569358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T19:41:33Z","timestamp":1784058093000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11569358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":46,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2026.3704709","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}