{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:13:00Z","timestamp":1778789580391,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["62572139"],"award-info":[{"award-number":["62572139"]}],"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":["U25A20424"],"award-info":[{"award-number":["U25A20424"]}],"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":["62572108"],"award-info":[{"award-number":["62572108"]}],"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":["62272121"],"award-info":[{"award-number":["62272121"]}],"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":["U2436208"],"award-info":[{"award-number":["U2436208"]}],"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":["62372129"],"award-info":[{"award-number":["62372129"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Program of Shandong","award":["2025CXPT082"],"award-info":[{"award-number":["2025CXPT082"]}]},{"name":"National Key Research and Development Plan","award":["2023YFB3107300"],"award-info":[{"award-number":["2023YFB3107300"]}]},{"name":"Guangdong S&T Program","award":["2024B0101010002"],"award-info":[{"award-number":["2024B0101010002"]}]},{"name":"Project of Guangdong Key Laboratory of Industrial Control System Security","award":["2024B1212020010"],"award-info":[{"award-number":["2024B1212020010"]}]},{"name":"Science and Technology Projects of Xizang Autonomous Region","award":["XZ202501ZY0026"],"award-info":[{"award-number":["XZ202501ZY0026"]}]},{"name":"Major Key Project of PCL","award":["PCL2024A05"],"award-info":[{"award-number":["PCL2024A05"]}]},{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education","award":["2024ZD016"],"award-info":[{"award-number":["2024ZD016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tbdata.2026.3657302","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:00:40Z","timestamp":1769202040000},"page":"994-1005","source":"Crossref","is-referenced-by-count":0,"title":["Accelerating Heterogeneous Tensor Parallelism via Flexible Workload Control"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1812-1068","authenticated-orcid":false,"given":"Zhigang","family":"Wang","sequence":"first","affiliation":[{"name":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9698-7310","authenticated-orcid":false,"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2653-0387","authenticated-orcid":false,"given":"Chuanfei","family":"Xu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7422-6254","authenticated-orcid":false,"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4120-7716","authenticated-orcid":false,"given":"Hui","family":"Lu","sequence":"additional","affiliation":[{"name":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1812-1316","authenticated-orcid":false,"given":"Dawei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9409-5359","authenticated-orcid":false,"given":"Zhihong","family":"Tian","sequence":"additional","affiliation":[{"name":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"LLAMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref2","first-page":"7480","article-title":"Scaling vision transformers to 22 Billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dehghani"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref5","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref6","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987554"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3275463"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE56470.2023.10043527"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3315847"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00043"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0480"},{"key":"ref13","article-title":"A 4D hybrid algorithm to scale parallel training to thousands of GPUs","author":"Singh","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605613"},{"key":"ref15","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref16","article-title":"Meta ai supercomputer DGX system overview","year":"2022"},{"key":"ref17","article-title":"Amazon EC2 on-demand pricing","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3202529"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3242200"},{"key":"ref20","article-title":"Tencent cloud - Resource management and scheduling overview","year":"2024"},{"key":"ref21","article-title":"Tencent cloud - cloud native scheduling overview","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2883613"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3228733"},{"key":"ref24","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref25","article-title":"Cifar image dataset","author":"Krizhevsky","year":"2009"},{"key":"ref26","article-title":"ImageNet large scale visual recognition dataset","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1206"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2016.7841777"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640375"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.107642"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.05.032"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.107846"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISORC61049.2024.10551324"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3040601"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-022-04422-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00052"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442538"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3274808.3274828"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3046440"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2974461"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3390109"},{"key":"ref44","first-page":"307","article-title":"$\\lbrace${HetPipe $\\rbrace$}: Enabling large $\\lbrace${ DNN$\\rbrace$} training on (whimpy) heterogeneous $\\lbrace${GPU$\\rbrace$} clusters through integration of pipelined model parallelism and data parallelism","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Park"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687317\/11517591\/11362926.pdf?arnumber=11362926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:59:47Z","timestamp":1778788787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11362926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2026.3657302","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"value":"2332-7790","type":"electronic"},{"value":"2372-2096","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}