{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T04:13:20Z","timestamp":1750997600302,"version":"3.41.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2682025CX127"],"award-info":[{"award-number":["2682025CX127"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018525","name":"Key Research and Development Program of Sichuan Province","doi-asserted-by":"publisher","award":["2021YFG0325"],"award-info":[{"award-number":["2021YFG0325"]}],"id":[{"id":"10.13039\/501100018525","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Technical Cooperation Project of Huawei","award":["ID H04W220751"],"award-info":[{"award-number":["ID H04W220751"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tpds.2025.3580098","type":"journal-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T19:01:26Z","timestamp":1750100486000},"page":"1680-1694","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Search With Improved Multi-Dimensional Dichotomy-Based Joint Optimization for Distributed Parallel Training of DNN"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0809-5799","authenticated-orcid":false,"given":"Guangyao","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}]},{"given":"Yiqin","family":"Fu","sequence":"additional","affiliation":[{"name":"China National Petroleum Corporation, Beijing, China"}]},{"given":"Haocheng","family":"Lan","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"given":"Yuanlun","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5551-9796","authenticated-orcid":false,"given":"Wenhong","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9754-6496","authenticated-orcid":false,"given":"Rajkumar","family":"Buyya","sequence":"additional","affiliation":[{"name":"Cloud Computing and Distributed Systems (CLOUDS) Laboratory, School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia"}]},{"given":"Jianhong","family":"Qian","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9517-2845","authenticated-orcid":false,"given":"Teng","family":"Su","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3111624"},{"key":"ref2","first-page":"1","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Wei"},{"article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown","key":"ref3"},{"article-title":"Scaling language models: Methods, analysis & insights from training gopher","year":"2021","author":"Rae","key":"ref4"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref5"},{"article-title":"The Llama 3 herd of models","year":"2024","author":"Dubey","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.06.021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2957478"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-03746-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10723-021-09550-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3343570"},{"key":"ref12","first-page":"1027","article-title":"Accelerating collective communication in data parallel training across deep learning frameworks","volume-title":"Proc. 19th USENIX Symp. Netw. Syst. Des. Implementation","author":"Romero"},{"key":"ref13","first-page":"6543","article-title":"TeraPipe: Token-level pipeline parallelism for training large-scale language models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref14","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586300"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356207"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508418"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00049"},{"key":"ref20","first-page":"559","article-title":"Alpa: Automating inter- and intra-operator parallelism for distributed deep learning","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Des. Implementation","author":"Zheng"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00111"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00056"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2020.11.005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3094364"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.10.072"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3041453"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00174"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507735"},{"key":"ref31","first-page":"7937","article-title":"Memory-efficient pipeline-parallel DNN training","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Narayanan"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD49262.2021.9437625"},{"key":"ref33","first-page":"58:1","article-title":"Efficient large-scale language model training on GPU clusters using Megatron-LM","volume-title":"Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal.","author":"Narayanan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527391"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3515804"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3138825"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11045205\/11037501.pdf?arnumber=11037501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T17:45:18Z","timestamp":1750959918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11037501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":38,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2025.3580098","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}