{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:16:37Z","timestamp":1775841397441,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0119301"],"award-info":[{"award-number":["2022ZD0119301"]}]},{"name":"Program of Zhejiang Province Science and Technology","award":["2022C01044"],"award-info":[{"award-number":["2022C01044"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2022-00151"],"award-info":[{"award-number":["226-2022-00151"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Starry Night Science Fund of Zhejiang University Shanghai Institute for Advanced Study","award":["SN-ZJU-SIAS-0010"],"award-info":[{"award-number":["SN-ZJU-SIAS-0010"]}]},{"name":"Key Laboratory for Corneal Diseases Research of Zhejiang Province"},{"name":"Alibaba Group through Alibaba Innovative Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tpds.2023.3279255","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T17:42:03Z","timestamp":1686246123000},"page":"2311-2324","source":"Crossref","is-referenced-by-count":6,"title":["P4SGD: Programmable Switch Enhanced Model-Parallel Training on Generalized Linear Models on Distributed FPGAs"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1387-7955","authenticated-orcid":false,"given":"Hongjing","family":"Huang","sequence":"first","affiliation":[{"name":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6497-6782","authenticated-orcid":false,"given":"Yingtao","family":"Li","sequence":"additional","affiliation":[{"name":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7030-0146","authenticated-orcid":false,"given":"Jie","family":"Sun","sequence":"additional","affiliation":[{"name":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7550-9379","authenticated-orcid":false,"given":"Xueying","family":"Zhu","sequence":"additional","affiliation":[{"name":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1720-3704","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7949-708X","authenticated-orcid":false,"given":"Liang","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3530-7662","authenticated-orcid":false,"given":"Jialin","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8550-9241","authenticated-orcid":false,"given":"Zeke","family":"Wang","sequence":"additional","affiliation":[{"name":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Beyond data and model parallelism for deep neural networks","author":"jia","year":"2018"},{"key":"ref12","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"shoeybi","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00048"},{"key":"ref15","article-title":"ZeRO & DeepSpeed: New system optimizations enable training models with over 100 billion parameters","year":"2020"},{"key":"ref14","article-title":"TeraPipe: Token-level pipeline parallelism for training large-scale language models","author":"li","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2993552"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056066"},{"key":"ref11","article-title":"One weird trick for parallelizing convolutional neural networks","author":"krizhevsky","year":"2014"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref17","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","author":"lao","year":"2021","journal-title":"Proc 18th USENIX Symp Netw Syst Des Implementation"},{"key":"ref16","article-title":"Scaling distributed machine learning with in-network aggregation","author":"sapio","year":"2019"},{"key":"ref19","article-title":"Wedge 100BF-32X R07","year":"2020"},{"key":"ref18","article-title":"Alveo U280 data center accelerator card data sheet","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446050"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236188"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080248"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.39"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2009.34"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3177540.3177561"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783710"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00028"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218538"},{"key":"ref9","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","author":"ho","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9834-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2118\/173208-MS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2014.21"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cps.2016.0021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00014"},{"key":"ref35","first-page":"1513","article-title":"ColumnSGD: A column-oriented framework for distributed stochastic gradient descent","author":"zhang","year":"2020","journal-title":"Proc IEEE Int Conf Data Eng"},{"key":"ref34","article-title":"NVIDIA system management interface","year":"2012"},{"key":"ref37","article-title":"GSPMD: General and scalable parallelization for ML computation graphs","author":"xu","year":"2021"},{"key":"ref36","article-title":"Alpa: Automating inter-and intra-operator parallelism for distributed deep learning","author":"zheng","year":"2022"},{"key":"ref31","article-title":"NVIDIA collective communication library (NCCL) documentation","year":"2020"},{"key":"ref30","article-title":"Accelerating GPU-storage communication with NVIDIA magum IO GPUDirect storage","year":"2021"},{"key":"ref33","article-title":"LM-sensors","year":"2019"},{"key":"ref32","article-title":"Alveo card management solution subsystem product guide (PG348)","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994515"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"ref39","first-page":"307","article-title":"HetPipe: Enabling large DNN training on (Whimpy) heterogeneous GPU clusters through integration of pipelined model parallelism and data parallelism","author":"park","year":"2020","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref38","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","author":"huang","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14778\/3317315.3317322"},{"key":"ref23","first-page":"277","article-title":"Concordia: Distributed shared memory with in-network cache coherence","author":"wang","year":"2021","journal-title":"Proc 19th USENIX Conf File Storage Technol"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00059"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00040"},{"key":"ref20","article-title":"Intel tofino programmable ethernet switch ASIC","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3405672.3405807"},{"key":"ref21","article-title":"Intel tofino 2 P4-programmable ethernet switch ASIC","year":"2021"},{"key":"ref28","article-title":"cuBLAS Release 12.1","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref29","article-title":"Getting started with CUDA graphs","year":"2019"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10153956\/10147044.pdf?arnumber=10147044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:53:51Z","timestamp":1689616431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10147044\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":56,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3279255","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":[[2023,8]]}}}