{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T15:43:19Z","timestamp":1787499799061,"version":"build-2736575974"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"US National Science Foundation","award":["#CNS-1419123"],"award-info":[{"award-number":["#CNS-1419123"]}]},{"name":"US National Science Foundation","award":["#IIS-1447804"],"award-info":[{"award-number":["#IIS-1447804"]}]},{"name":"US National Science Foundation","award":["#ACI-1450440"],"award-info":[{"award-number":["#ACI-1450440"]}]},{"name":"US National Science Foundation","award":["#CNS-1513120"],"award-info":[{"award-number":["#CNS-1513120"]}]},{"name":"US National Science Foundation","award":["#IIS-1636846"],"award-info":[{"award-number":["#IIS-1636846"]}]},{"name":"US National Science Foundation","award":["OCI-1053575"],"award-info":[{"award-number":["OCI-1053575"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multi-Scale Comp. Syst."],"published-print":{"date-parts":[[2018,10,1]]},"DOI":"10.1109\/tmscs.2018.2845886","type":"journal-article","created":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T15:03:52Z","timestamp":1528729432000},"page":"635-648","source":"Crossref","is-referenced-by-count":16,"title":["DLoBD: A Comprehensive Study of Deep Learning over Big Data Stacks on HPC Clusters"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7581-8905","authenticated-orcid":false,"given":"Xiaoyi","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajarshi","family":"Biswas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2812-1045","authenticated-orcid":false,"given":"M. Haseeb","family":"Javed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhabaleswar K.","family":"Panda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2017.24"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2016.7840611"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.83"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2015.161"},{"key":"ref13","article-title":"Tensorframes: Tensorflow wrapper for Dataframes on Apache Spark","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206800"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-014-0007-7"},{"key":"ref4","article-title":"SparkNet: Training deep networks in spark","author":"moritz","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2014.2325029"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2945397"},{"key":"ref6","article-title":"BigDL: A distributed deep learning framework for big data","author":"dai","year":"2018","journal-title":"arXiv preprint arXiv 1804 02671"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2017.19"},{"key":"ref5","article-title":"Deeplearning4j: Open-Source Distributed Deep Learning for the JVM","year":"2018"},{"key":"ref8","article-title":"CuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014"},{"key":"ref7","article-title":"Flexible and scalable deep learning with MMLSpark","author":"hamilton","year":"0","journal-title":"arXiv preprint arXiv 1804 02671"},{"key":"ref2","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"Proc USENIX Symp Operat Syst Des Implement"},{"key":"ref9","first-page":"167","article-title":"Intel Math Kernel Library","author":"wang","year":"2014","journal-title":"High Performance Computing and Communications"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2616498.2616540"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018769"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.78"},{"key":"ref24","article-title":"Distributed TensorFlow with MPI","author":"vishnu","year":"2016","journal-title":"arXiv preprint arXiv 1603 02895"},{"key":"ref23","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","author":"zhang","year":"2017","journal-title":"USENIX Annu Tech Conf"},{"key":"ref26","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"sergeev","year":"2018","journal-title":"arXiv preprint arxiv 1802 05807"},{"key":"ref25","article-title":"Bringing HPC techniques to deep learning.","year":"0"}],"container-title":["IEEE Transactions on Multi-Scale Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/6687315\/8630102\/8378049-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6687315\/8630102\/08378049.pdf?arnumber=8378049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T14:54:26Z","timestamp":1649429666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8378049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,1]]},"references-count":30,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmscs.2018.2845886","relation":{},"ISSN":["2332-7766","2372-207X"],"issn-type":[{"value":"2332-7766","type":"electronic"},{"value":"2372-207X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,1]]}}}