{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:40:15Z","timestamp":1777488015497,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T00:00:00Z","timestamp":1663545600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T00:00:00Z","timestamp":1663545600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,19]]},"DOI":"10.1109\/hpec55821.2022.9926375","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:40:48Z","timestamp":1667526048000},"page":"1-8","source":"Crossref","is-referenced-by-count":10,"title":["Benchmarking Resource Usage for Efficient Distributed Deep Learning"],"prefix":"10.1109","author":[{"given":"Nathan C.","family":"Frey","sequence":"first","affiliation":[{"name":"MIT Lincoln Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baolin","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"McDonald","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Zhao","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Jones","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Bestor","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devesh","family":"Tiwari","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vijay","family":"Gadepally","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddharth","family":"Samsi","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581275"},{"key":"ref2","author":"Ahmed","year":"2020","journal-title":"The de-democratization of ai: Deep learning and the compute divide in artificial intelligence research"},{"key":"ref3","author":"Bello","year":"2021","journal-title":"Revisiting resnets: Improved training and scaling strategies"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"ref5","author":"Bronstein","year":"2021","journal-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref7","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin"},{"key":"ref8","volume-title":"W. Pytorch lightning","author":"Falcon","year":"2019"},{"key":"ref9","article-title":"Fast graph representation learning with PyTorch Geometric","volume-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds","author":"Fey"},{"key":"ref10","article-title":"Scalable geometric deep learning on molecular graphs","volume-title":"NeurIPS 2021 AI for Science Workshop","author":"Frey"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.07.007"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00074"},{"key":"ref15","article-title":"Neural tangent ker-nel: Convergence and generalization in neural networks","volume":"abs\/1806.07572","author":"Jacot","year":"2018","journal-title":"CoRR"},{"key":"ref16","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Jeon"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622396"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-016-9938-8"},{"key":"ref19","author":"Kingma","year":"2017","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref20","author":"Klicpera","year":"2020","journal-title":"Fast and uncertainty-aware directional message passing for non-equilibrium molecules"},{"key":"ref21","author":"Klicpera","year":"2020","journal-title":"Directional message passing for molecular graphs"},{"key":"ref22","article-title":"Quan-tifying the carbon emissions of machine learning","author":"Lacoste","year":"2019","journal-title":"arXiv preprint"},{"key":"ref23","author":"Li","year":"2020","journal-title":"Pytorch distributed: Experiences on accelerating data parallel training"},{"key":"ref24","author":"Merity","year":"2016","journal-title":"Pointer sentinel mixture models"},{"key":"ref25","author":"Park","year":"2018","journal-title":"Deep learning inference in facebook data centers: Characterization, performance optimizations and hardware implications"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00087"},{"key":"ref27","author":"Patterson","year":"2021","journal-title":"Carbon emissions and large neural network training"},{"key":"ref28","article-title":"Paleo: A performance model for deep neural networks","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"QI"},{"key":"ref29","author":"Radosavovic","year":"2020","journal-title":"Designing network design spaces"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.22"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2018.8547629"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286149"},{"key":"ref33","author":"Samsi","year":"2021","journal-title":"The mit supercloud dataset"},{"key":"ref34","author":"Schutt","year":"2017","journal-title":"Schnet: A continuous-filter convolutional neural network for modeling quantum interactions"},{"key":"ref35","author":"Sharir","year":"2020","journal-title":"The cost of training nlp models: A concise overview"},{"key":"ref36","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs\/1409.1556","author":"Simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7123"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref39","author":"Tan","year":"2020","journal-title":"Efficientnet: Rethinking model scaling for convolutional neural networks"},{"key":"ref40","author":"Thompson","year":"2020","journal-title":"The computational limits of deep learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2017.8335698"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/DLS49591.2019.00016"},{"key":"ref43","article-title":"Predicting training time without training","volume":"abs\/2008.12478","author":"Zancato","year":"2020","journal-title":"CoRR"},{"key":"ref44","author":"Zoph","year":"2017","journal-title":"Neural architecture search with reinforcement learning"}],"event":{"name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","location":"Waltham, MA, USA","start":{"date-parts":[[2022,9,19]]},"end":{"date-parts":[[2022,9,23]]}},"container-title":["2022 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9926284\/9926287\/09926375.pdf?arnumber=9926375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T06:18:18Z","timestamp":1706077098000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9926375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/hpec55821.2022.9926375","relation":{},"subject":[],"published":{"date-parts":[[2022,9,19]]}}}