{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T21:48:08Z","timestamp":1791236888818,"version":"4.1.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1814920"],"award-info":[{"award-number":["1814920"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DoD ARO","award":["W911NF-19-1-0484"],"award-info":[{"award-number":["W911NF-19-1-0484"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/tpds.2022.3144614","type":"journal-article","created":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T16:26:42Z","timestamp":1642782402000},"page":"2496-2508","source":"Crossref","is-referenced-by-count":87,"title":["Coordinated Batching and DVFS for DNN Inference on GPU Accelerators"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5123-6318","authenticated-orcid":false,"given":"Seyed Morteza","family":"Nabavinejad","sequence":"first","affiliation":[{"name":"School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8232-4516","authenticated-orcid":false,"given":"Sherief","family":"Reda","sequence":"additional","affiliation":[{"name":"School of Engineering, Brown University, Providence, RI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7877-6712","authenticated-orcid":false,"given":"Masoumeh","family":"Ebrahimi","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3307772.3328315"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330373"},{"key":"ref33","first-page":"4278","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref32","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015"},{"key":"ref31","article-title":"Tensorflow-slim image classification model library","author":"silberman","year":"2016"},{"key":"ref30","year":"0"},{"key":"ref37","first-page":"613","article-title":"Clipper: A low-latency online prediction serving system","author":"crankshaw","year":"2017","journal-title":"Proc USENIX Symp Netw Syst Des Implementation"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006606"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2021.3123695"},{"key":"ref29","first-page":"2951","article-title":"Practical Bayesian optimization of machine learning algorithms","author":"snoek","year":"2012","journal-title":"Proc Adv Neural Informat Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2021.3066142"},{"key":"ref22","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref23","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref26","first-page":"469","article-title":"CherryPick: Adaptively unearthing the best cloud configurations for big data analytics","author":"alipourfard","year":"2017","journal-title":"Proc 14th USENIX Symp Netw Syst Des Implementation"},{"key":"ref25","article-title":"The caltech-256: Caltech technical report","volume":"7694","author":"griffin","year":"2007","journal-title":"Vol"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853595"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC.2019.8669031"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431535"},{"key":"ref57","article-title":"RapiDNN: In-memory deep neural network acceleration framework","author":"imani","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-29"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED.2019.8824944"},{"key":"ref53","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"molchanov","year":"2016"},{"key":"ref52","article-title":"Pruning filters for efficient convnets","author":"li","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2019.2951083"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2013.6657064"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IGCC.2018.8752132"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2019.2942020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2015.7054182"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2018.02.001"},{"key":"ref16","article-title":"Nvidia system management interface","year":"0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.47"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-32"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3423136"},{"key":"ref3","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Informat Process Sys"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359658"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3418498"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.25"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123970"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378534"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3358192"},{"key":"ref46","article-title":"Queueing analysis of GPU-based inference servers with dynamic batching: A closed-form characterization","volume":"147","author":"inoue","year":"2020","journal-title":"Perform Eval"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414648"},{"key":"ref47","article-title":"Dynamic network surgery for efficient dnns","author":"guo","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133045"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.52"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00334"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/9732246\/9689937-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9732246\/09689937.pdf?arnumber=9689937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T16:12:40Z","timestamp":1658765560000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9689937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":58,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3144614","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}