{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T05:30:53Z","timestamp":1777354253477,"version":"3.51.4"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021YFB0300300"],"award-info":[{"award-number":["2021YFB0300300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072165"],"award-info":[{"award-number":["62072165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpds.2022.3187815","type":"journal-article","created":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T19:17:35Z","timestamp":1657048655000},"page":"4326-4338","source":"Crossref","is-referenced-by-count":13,"title":["AccTFM: An Effective Intra-Layer Model Parallelization Strategy for Training Large-Scale Transformer-Based Models"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4745-5331","authenticated-orcid":false,"given":"Zihao","family":"Zeng","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, National Supercomputing Center in Changsha, Hunan University, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2372-6715","authenticated-orcid":false,"given":"Chubo","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, National Supercomputing Center in Changsha, Hunan University, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9081-8153","authenticated-orcid":false,"given":"Zhuo","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, National Supercomputing Center in Changsha, Hunan University, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2635-7716","authenticated-orcid":false,"given":"Kenli","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, National Supercomputing Center in Changsha, Hunan University, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-4048","authenticated-orcid":false,"given":"Keqin","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, National Supercomputing Center in Changsha, Hunan University, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586300"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2909473"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356207"},{"key":"ref30","first-page":"1232","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref10","first-page":"103","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","author":"huang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052862"},{"key":"ref12","first-page":"132","article-title":"Priority-based parameter propagation for distributed dnn training","author":"jayarajan","year":"2019","journal-title":"Proc Mach Learn Syst"},{"key":"ref13","first-page":"418","article-title":"TicTac: Accelerating distributed deep learning with communication scheduling","author":"hashemi","year":"2019","journal-title":"Proc Mach Learn Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155446"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356222"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00220"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3084104"},{"key":"ref28","first-page":"479","article-title":"Pipelined backpropagation at scale: Training large models without batches","author":"kosson","year":"2021","journal-title":"Proc Mach Learn Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref27","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","author":"zhang","year":"2017","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref29","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","author":"lian","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2877359"},{"key":"ref1","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref22","article-title":"XPipe: Efficient pipeline model parallelism for multi-GPU DNN training","author":"guan","year":"2019"},{"key":"ref21","article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","author":"shoeybi","year":"2019"},{"key":"ref24","first-page":"10435","article-title":"Mesh-TensorFlow: Deep learning for supercomputers","author":"shazeer","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"269","article-title":"PipeMare: Asynchronous pipeline parallel DNN training","author":"yang","year":"2021","journal-title":"Proc Mach Learn Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018769"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9790018\/09815837.pdf?arnumber=9815837","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T19:58:26Z","timestamp":1663617506000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9815837\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":37,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3187815","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":[[2022,12,1]]}}}