{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T18:01:42Z","timestamp":1725732102704},"reference-count":43,"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\/hpec55821.2022.9926390","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:40:48Z","timestamp":1667526048000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["DASH: Scheduling Deep Learning Workloads on Multi-Generational GPU-Accelerated Clusters"],"prefix":"10.1109","author":[{"given":"Baolin","family":"Li","sequence":"first","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tirthak","family":"Patel","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":"Karen","family":"Gettings","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"}]},{"given":"Devesh","family":"Tiwari","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356202"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1116-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3146347.3146353"},{"key":"ref8","article-title":"Image classification at supercomputer scale","author":"Ying","year":"2018","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Extremely large minibatch sgd: Training resnet-50 on imagenet in 15 minutes","author":"Akiba","year":"2017","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Highly scalable deep learning training system with mixed-precision: Training imagenet in four minutes","author":"Jia","year":"2018","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006550"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","article-title":"Bert: Pre-training of deep bidi-rectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"13th {USENIX} Symposium on Operating Systems Design and Implementation({ OSDI} 18)","author":"Xiao"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref21","first-page":"485","article-title":"Tiresias: A {GPU} cluster manager for distributed deep learning","volume-title":"16th {USENIX} Symposium on Networked Systems Design and Implementation ({NSDI}19)","author":"Gu"},{"key":"ref22","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref24","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00293"},{"key":"ref27","first-page":"1049","article-title":"Mark: Exploiting cloud services for cost-effective, slo-aware machine learning inference serving","volume-title":"2019 {USENIX} Annual Technical Conference ({USENIX}{ATC}19)","author":"Zhang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2010"},{"key":"ref29","article-title":"The architectural implications of facebook\u2019s dnn-based personalized recommendation","author":"Gupta","year":"2019","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Recnmp: Accelerating personalized recommen-dation with near-memory processing","author":"Ke","year":"2019","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2019.00024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00036"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476168"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref35","article-title":"Accelerated training for cnn distributed deep learning through automatic resource-aware layer placement","author":"Park","year":"2019","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Pipedream: Fast and efficient pipeline parallel dnn training","author":"Harlap","year":"2018","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Themis: Fair and efficient gpu cluster scheduling for machine learning workloads","author":"Mahajan","year":"2019","journal-title":"ar Xiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035933"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2018.00014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622863"},{"key":"ref41","article-title":"Hetpipe: Enabling large dnn train-ling on (whimpy) heterogeneous gpu clusters through integration of pipelined model parallelism and data parallelism","author":"Park","year":"2020","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.151"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387547"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref45","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","volume-title":"14th {USENIX} Symposium on Operating Systems Design and Implementation ({ OSDI} 20)","author":"Narayanan"},{"key":"ref46","first-page":"81","article-title":"Single-isa heterogeneous multi-core archi-tectures: The potential for processor power reduction","volume-title":"Proceedings. 36th Annual IEEE\/ACM International Symposium on Microarchitecture, 2003. MICRO-36","author":"Kumar"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1629911.1630149"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400691"}],"event":{"name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2022,9,19]]},"location":"Waltham, MA, USA","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\/09926390.pdf?arnumber=9926390","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T04:02:04Z","timestamp":1706068924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9926390\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/hpec55821.2022.9926390","relation":{},"subject":[],"published":{"date-parts":[[2022,9,19]]}}}