{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:19:53Z","timestamp":1740169193505,"version":"3.37.3"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572325","60970012"],"award-info":[{"award-number":["61572325","60970012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education Doctoral Fund of Ph.D. Supervisor of China","award":["20113120110008"],"award-info":[{"award-number":["20113120110008"]}]},{"name":"Shanghai Key Science and Technology Project in Information Technology Field","award":["14511107902","16DZ1203603"],"award-info":[{"award-number":["14511107902","16DZ1203603"]}]},{"DOI":"10.13039\/501100012150","name":"Shanghai Leading Academic Discipline775 Project","doi-asserted-by":"publisher","award":["XTKX2012"],"award-info":[{"award-number":["XTKX2012"]}],"id":[{"id":"10.13039\/501100012150","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Engineering Research Center Project","award":["GCZX14014","C14001"],"award-info":[{"award-number":["GCZX14014","C14001"]}]},{"name":"a Cooperation Project with the Intel Asia Pacific Research and Development Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2999096","type":"journal-article","created":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T21:32:05Z","timestamp":1591047125000},"page":"103256-103272","source":"Crossref","is-referenced-by-count":4,"title":["BPCM: A Flexible High-Speed Bypass Parallel Communication Mechanism for GPU Cluster"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9309-4311","authenticated-orcid":false,"given":"Mingjie","family":"Wu","sequence":"first","affiliation":[]},{"given":"Qingkui","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jingjuan","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"4238","article-title":"BML: A high-performance, low-cost gradient synchronization algorithm for DML training","author":"wang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3229543.3229544"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737367"},{"key":"ref13","article-title":"Highly scalable deep learning training system with mixed-precision: Training ImageNet in four minutes","author":"jia","year":"2018","journal-title":"arXiv 1807 11205"},{"key":"ref14","article-title":"Massively distributed SGD: ImageNet\/ResNet-50 training in a flash","author":"mikami","year":"2018","journal-title":"arXiv 1811 05233"},{"key":"ref15","article-title":"Image classification at supercomputer scale","author":"ying","year":"2018","journal-title":"arXiv 1811 06992"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3123878.3131975"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"journal-title":"Nvidia DGX-1","year":"2017","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/PAAP.2018.00018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737595"},{"journal-title":"Data Plane Development Kit Project Page","year":"2014","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/NAS.2015.7255208"},{"journal-title":"NVIDIA DGX-2","year":"2018","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/NOF.2014.7119762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/EWSDN.2014.33"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4018\/IJAEC.2016040104"},{"key":"ref2","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"sergeev","year":"2018","journal-title":"arXiv 1802 05799"},{"key":"ref9","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","author":"zhang","year":"2017","journal-title":"Proc of USENIX Annual Technical Conf (USENIX)"},{"article-title":"Multi-tenant GPU clusters for deep learning workloads: Analysis and implications","year":"2018","author":"jeon","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947013"},{"journal-title":"NVIDIA NVSWITCH","year":"2018","key":"ref22"},{"journal-title":"NVIDIA NVLink","year":"2017","key":"ref21"},{"journal-title":"Massively Scale Your Deep Learning Training with NCCL 2 4","year":"2019","key":"ref24"},{"journal-title":"PCI Express - An Overview of the PCI Express Standard","year":"2014","key":"ref23"},{"key":"ref26","article-title":"Blink: Fast and generic collectives for distributed ML","author":"wang","year":"2019","journal-title":"arXiv 1910 04940"},{"journal-title":"Accelerating Machine Learning for Computer Vision","year":"2017","key":"ref25"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09104965.pdf?arnumber=9104965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:52:25Z","timestamp":1639770745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9104965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2999096","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}