{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:08:43Z","timestamp":1790701723627,"version":"4.1.0"},"reference-count":91,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/iiswc.2018.8573476","type":"proceedings-article","created":{"date-parts":[[2018,12,13]],"date-time":"2018-12-13T19:48:21Z","timestamp":1544730501000},"page":"88-100","source":"Crossref","is-referenced-by-count":104,"title":["Benchmarking and Analyzing Deep Neural Network Training"],"prefix":"10.1109","author":[{"given":"Hongyu","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Akrout","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bojian","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Pelegris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anand","family":"Jayarajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amar","family":"Phanishayee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bianca","family":"Schroeder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gennady","family":"Pekhimenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref71","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037746"},{"key":"ref76","article-title":"Maximizing cnn accelerator efficiency through resource partitioning","author":"shen","year":"2016","journal-title":"arXiv preprint arXiv 1607 00064"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CCBD.2016.029"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"ref39","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv preprint arXiv 1706 02677"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"ref79","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref33","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080248"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"ref30","article-title":"Torch7: A matlab-like environment for machine learning","author":"collobert","year":"2011","journal-title":"BigLearn NIPS Workshop"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830789"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124552"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.29"},{"key":"ref62","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"7540","journal-title":"Nature"},{"key":"ref28","author":"chollet","year":"2015","journal-title":"Keras"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","first-page":"571","article-title":"Project adam: Building an efficient and scalable deep learning training system","volume":"14","author":"suzue","year":"2014","journal-title":"OSDI"},{"key":"ref65","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref29","article-title":"A downsampled variant of imagenet as an alternative to the cifar datasets","author":"chrabaszcz","year":"2017","journal-title":"arXiv preprint arXiv 1707 07816"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123979"},{"key":"ref68","author":"paszke","year":"2017","journal-title":"On Automatic Differentiation"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132785"},{"key":"ref2","year":"0","journal-title":"Cnn benchmarks"},{"key":"ref1","year":"0","journal-title":"The Benchmarking Process"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446049"},{"key":"ref22","article-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref21","article-title":"The iwslt 2015 evaluation campaign","author":"cettolo","year":"2015","journal-title":"IWSLT 2015 International Workshop on Spoken Language Translation"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001140"},{"key":"ref25","article-title":"cudnn: Efficient primitives for deep learning","author":"chetlur","year":"2014","journal-title":"arXiv preprint arXiv 1410 0759"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00070"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783724"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080215"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001164"},{"key":"ref58","first-page":"3","article-title":"Scaling distributed machine learning with the parameter server","volume":"1","author":"li","year":"2014","journal-title":"OSDI"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref56","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.41"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783722"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"ref40","first-page":"5769","article-title":"Improved training of wasserstein gans","author":"gulrajani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"ref13","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref14","article-title":"Wasserstein gan","author":"arjovsky","year":"2017","journal-title":"arXiv preprint arXiv 1701 00295"},{"key":"ref15","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref82","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"153","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref81","article-title":"Chainer: a next-generation open source framework for deep learning","volume":"5","author":"tokui","year":"2015","journal-title":"Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Twenty-ninth Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref17","first-page":"1","article-title":"Theano: A cpu and gpu math compiler in python","author":"bergstra","year":"2010","journal-title":"Proc 9th Python in Science Conf"},{"key":"ref84","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/978-3-319-06486-4_7","article-title":"Intel math kernel library","author":"wang","year":"2014","journal-title":"High-Performance Computing on the Intel® Xeon Phi"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3302"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"ref19","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"arXiv preprint arXiv 1604 07316"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref89","author":"yu","year":"2014","journal-title":"An Introduction to Computational Networks and the Computational Network Toolkit"},{"key":"ref4","year":"0"},{"key":"ref3","year":"0","journal-title":"convnet-benchmarks"},{"key":"ref6","year":"0"},{"key":"ref5","year":"0"},{"key":"ref85","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv preprint arXiv 1609 09861"},{"key":"ref8","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"OSDI"},{"key":"ref86","first-page":"669","article-title":"Tux2: Distributed graph computation for machine learning","author":"xiao","year":"2017","journal-title":"NSDI"},{"key":"ref7","year":"2018"},{"key":"ref49","article-title":"An empirical evaluation of deep learning on highway driving","author":"huval","year":"2015","journal-title":"arXiv preprint arXiv 1504 01716"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953159"},{"key":"ref88","article-title":"Imagenet training in minutes","author":"you","year":"2017","journal-title":"CoRR abs\/1709 05011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581275"},{"key":"ref46","article-title":"Sockeye: A toolkit for neural machine translation","author":"hieber","year":"2017","journal-title":"arXiv preprint arXiv 1712 05690"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref48","first-page":"629","article-title":"Gaia: Geo-distributed machine learning approaching lan speeds","author":"hsieh","year":"2017","journal-title":"NSDI"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref42","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2015","journal-title":"arXiv preprint arXiv 1510 00149"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749472"}],"event":{"name":"2018 IEEE International Symposium on Workload Characterization (IISWC)","location":"Raleigh, NC","start":{"date-parts":[[2018,9,30]]},"end":{"date-parts":[[2018,10,2]]}},"container-title":["2018 IEEE International Symposium on Workload Characterization (IISWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8554060\/8573472\/08573476.pdf?arnumber=8573476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T12:38:19Z","timestamp":1775306299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8573476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/iiswc.2018.8573476","relation":{},"subject":[],"published":{"date-parts":[[2018,9]]}}}