{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T01:24:28Z","timestamp":1776993868337,"version":"3.51.4"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"National Science and Technology Major Project of China MIIT","award":["2018ZX03001001-003"],"award-info":[{"award-number":["2018ZX03001001-003"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2916550","type":"journal-article","created":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T19:53:12Z","timestamp":1557863592000},"page":"64788-64797","source":"Crossref","is-referenced-by-count":34,"title":["Iteration Time Prediction for CNN in Multi-GPU Platform: Modeling and Analysis"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0443-9582","authenticated-orcid":false,"given":"Ziqian","family":"Pei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chensheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guo","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"1","article-title":"Imagenet training in minutes","author":"you","year":"2018","journal-title":"Proc 47th Int Conf Parallel Process"},{"key":"ref32","first-page":"1058","article-title":"1-bit stochastic gradient descent and application to data-parallel distributed training of speech DNNs","author":"seide","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref31","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"},{"key":"ref30","year":"2018","journal-title":"NVIDIA CUDA C Programming Guide"},{"key":"ref35","first-page":"137","article-title":"Hardware-aware machine learning: Modeling and optimization","author":"marculescu","year":"2018","journal-title":"Proc Int Conf Comput -Aided Design"},{"key":"ref34","author":"tan","year":"2018","journal-title":"MnasNet Platform-Aware Neural Architecture Search for Mobile"},{"key":"ref10","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"Proc 11th USENIX Conf Oper Syst Design Implement"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref12","author":"chen","year":"2015","journal-title":"Mxnet A flexible and efficient machine learning library for heterogeneous distributed systems"},{"key":"ref13","author":"chetlur","year":"2014","journal-title":"cuDNN Efficient Primitives for Deep Learning"},{"key":"ref14","author":"krizhevsky","year":"2014","journal-title":"One weird trick for parallelizing convolutional neural networks"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CCBD.2016.029"},{"key":"ref16","author":"cai","year":"2017","journal-title":"Neuralpower Predict and deploy energy-efficient convolutional neural networks"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079083"},{"key":"ref18","first-page":"583","article-title":"Scaling distributed machine learning with the parameter server","volume":"14","author":"li","year":"2014","journal-title":"Proc OSDI"},{"key":"ref19","author":"luehr","year":"2016","journal-title":"Fast Multi-GPU Collectives With NCCL"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref4","author":"han","year":"2016","journal-title":"ESE Efficient speech recognition engine with sparse LSTM on FPGA"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-017-1994-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","author":"ben-nun","year":"2018","journal-title":"Demystifying parallel and distributed deep learning An in-depth concurrency analysis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref5","author":"wu","year":"2016","journal-title":"Google’s neural machine translation system Bridging the gap between human and machine translation"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.917757"},{"key":"ref2","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref9","author":"chrysos","year":"2014","journal-title":"Intel Xeon Phi Coprocessor-the Architecture"},{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","year":"2017","journal-title":"Baidu allreduce"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2016.7840590"},{"key":"ref21","year":"2018","journal-title":"CUBLAS Library Documentation"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783270"},{"key":"ref23","article-title":"Paleo: A performance model for deep neural networks","author":"qi","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref26","author":"mathieu","year":"2013","journal-title":"Fast training of convolutional networks through ffts"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/DASC\/PiCom\/DataCom\/CyberSciTec.2018.000-4"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08713989.pdf?arnumber=8713989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T02:50:41Z","timestamp":1643165441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8713989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2916550","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}