{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:31:32Z","timestamp":1776213092195,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000005","name":"U.S. Department of Defense","doi-asserted-by":"publisher","award":["#GS04T09DBC0017"],"award-info":[{"award-number":["#GS04T09DBC0017"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2019,3,1]]},"DOI":"10.1109\/tpds.2018.2867222","type":"journal-article","created":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T03:00:22Z","timestamp":1535425222000},"page":"575-588","source":"Crossref","is-referenced-by-count":16,"title":["Exploiting Hardware Multicast and GPUDirect RDMA for Efficient Broadcast"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6752-3135","authenticated-orcid":false,"given":"Ching-Hsiang","family":"Chu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7581-8905","authenticated-orcid":false,"given":"Xiaoyi","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6272-3760","authenticated-orcid":false,"given":"Ammar A.","family":"Awan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1200-2754","authenticated-orcid":false,"given":"Hari","family":"Subramoni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6449-1310","authenticated-orcid":false,"given":"Bracy","family":"Elton","sequence":"additional","affiliation":[]},{"given":"Dhabaleswar K.","family":"Panda","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref33","article-title":"Fast and scalable MPI-level broadcast using InfiniBand's hardware multicast support","author":"liu","year":"2004","journal-title":"Proc 18th Int Parallel Distrib Process Symp"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2014.7116873"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.17"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.25"},{"key":"ref37","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503286"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2488551.2488573"},{"key":"ref10","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems.","author":"abadi","year":"2015"},{"key":"ref40","year":"2018"},{"key":"ref11","article-title":"The Microsoft cognitive toolkit.","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom.2016.0036"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref14","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-006-0019-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370475"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2006.1639562"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2014.7116875"},{"key":"ref19","year":"2018"},{"key":"ref28","article-title":"Optimized broadcast for deep learning workloads on dense-GPU InfiniBand clusters: MPI or NCCL?","volume":"abs 1707 9414","author":"awan","year":"2017","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2321742"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2966884.2966912"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.2014.2330608"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1007\/978-3-642-33518-1_16","article-title":"OMB-GPU: A micro-benchmark suite for evaluating MPI libraries on GPU clusters","author":"bureddy","year":"2012","journal-title":"Proc 19th Eur Conf Recent Adv Message Passing Interf"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2016.16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.228"},{"key":"ref8","article-title":"Caffe: A fast open framework for deep learning.","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1117\/12.642809"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018769"},{"key":"ref9","article-title":"A new lightweight, modular, and scalable deep learning framework.","year":"2016"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2432809"},{"key":"ref20","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.335"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536478"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2831129.2831131"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2007.59"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2014.7097919"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14313-2_35"},{"key":"ref26","article-title":"Optimized primitives for collective multi-GPU communication.","year":"2016"},{"key":"ref43","article-title":"High performance processing of streaming data","author":"kamburugamuve","year":"2015","journal-title":"Proc IEEE 22nd Int Conf High Perform Comput Workshops"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2015.20"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/71\/8640283\/8447246-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8640283\/08447246.pdf?arnumber=8447246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:53:48Z","timestamp":1657745628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8447246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,1]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2018.2867222","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":[[2019,3,1]]}}}