{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:46:16Z","timestamp":1761324376163,"version":"3.37.3"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF) Grant through the Korean Government [Ministry of Science and ICT (MSIT)]","doi-asserted-by":"publisher","award":["NRF-2020R1G1A1012170"],"award-info":[{"award-number":["NRF-2020R1G1A1012170"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3088861","type":"journal-article","created":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T20:05:02Z","timestamp":1623701102000},"page":"85403-85417","source":"Crossref","is-referenced-by-count":11,"title":["ODMDEF: On-Device Multi-DNN Execution Framework Utilizing Adaptive Layer-Allocation on General Purpose Cores and Accelerators"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9754-5001","authenticated-orcid":false,"given":"Cheolsun","family":"Lim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4254-4009","authenticated-orcid":false,"given":"Myungsun","family":"Kim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1145\/2964284.2973801"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/JPROC.2017.2761740"},{"year":"2020","journal-title":"Nvidia Cuda Memory Management","key":"ref33"},{"year":"2020","journal-title":"Jetson-Zero-Copy","key":"ref32"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/RTSS.2017.00017"},{"year":"2019","journal-title":"Cuda-stream","key":"ref30"},{"key":"ref37","article-title":"CuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014","journal-title":"Arxiv 1410 0759"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1145\/3293883.3295734"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1007\/978-1-4614-7138-7"},{"key":"ref34","volume":"936","author":"seber","year":"2012","journal-title":"Linear Regression Analysis"},{"year":"2019","journal-title":"Introduction to tensorflow lite","key":"ref60"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1109\/CVPR.2018.00286"},{"year":"2019","journal-title":"Caffe","key":"ref28"},{"year":"2019","journal-title":"TensorFlow™","key":"ref27"},{"year":"2019","journal-title":"Torch","key":"ref29"},{"key":"ref2","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"arXiv 1604 07316 [cs]"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ROBIO.2017.8324578"},{"key":"ref20","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 26th Conf Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ISCAS.2018.8351550"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/s00138-019-01042-8"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1002\/spe.2285"},{"key":"ref23","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"year":"2016","author":"higginbotham","article-title":"Google takes unconventional route with homegrown machine learning chips","key":"ref26"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/RTCSA.2015.10"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1109\/ISSCC.2015.7062935"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1145\/2742060.2743766"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1145\/2973750.2973777"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1109\/IPSN.2016.7460664"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.3390\/electronics8111321"},{"key":"ref56","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref55","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1109\/ICCD.2013.6657019"},{"key":"ref53","first-page":"1737","article-title":"Deep learning with limited numerical precision","author":"gupta","year":"2015","journal-title":"Proc ICML"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1145\/2749469.2750389"},{"year":"2019","journal-title":"Nvidia Hyper-Q","key":"ref10"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/JSSC.2016.2616357"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1145\/2935643.2935650"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/3007787.3001179"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/MICRO.2014.58"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/2541940.2541967"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ACCESS.2020.2996596"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1016\/j.jpdc.2017.08.012"},{"year":"2019","journal-title":"Nvidia CUBLAS","key":"ref17"},{"year":"2020","journal-title":"CUDA Multi-Process Service","key":"ref18"},{"key":"ref19","first-page":"45","article-title":"$\\mu$\nLayer: Low latency on-device inference using cooperative single-layer acceleration and processor-friendly quantization","author":"kim","year":"2019","journal-title":"Proc 14th EuroSys Conf"},{"key":"ref4","first-page":"515","article-title":"Farmbeats: An IoT platform for data-driven agriculture","author":"vasisht","year":"2017","journal-title":"Proc NSDI"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1145\/3173162.3173191"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1145\/2648584.2648589"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1145\/2988450.2988454"},{"year":"2019","journal-title":"NVIDIA CUDA4 0 Toolkit","key":"ref8"},{"year":"2019","journal-title":"NVIDIA Jetson AGX Xavier","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1109\/CVPRW.2014.106"},{"year":"2019","journal-title":"Nvidia cuDNN","key":"ref9"},{"key":"ref46","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","author":"mirhoseini","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref45","first-page":"1","article-title":"Hierarchical planning for device placement","author":"mirhoseini","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1145\/1815961.1815993"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/ASAP.2009.25"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1145\/2872362.2872368"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1145\/3081333.3081360"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1109\/RTSS46320.2019.00042"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1145\/3037697.3037700"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09453793.pdf?arnumber=9453793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:34Z","timestamp":1639770994000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9453793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3088861","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}