{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T09:17:05Z","timestamp":1725700625238},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T00:00:00Z","timestamp":1698624000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T00:00:00Z","timestamp":1698624000000},"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":[[2023,10,30]]},"DOI":"10.1109\/milcom58377.2023.10356363","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:37:01Z","timestamp":1703533021000},"page":"39-44","source":"Crossref","is-referenced-by-count":0,"title":["M3: Towards Efficient Mixed Machine Learning Model Co-Location on Constrained Edge Devices"],"prefix":"10.1109","author":[{"given":"Luis Angel D.","family":"Bathen","sequence":"first","affiliation":[{"name":"IBM Research,Almaden,USA"}]},{"given":"Simeon","family":"Babatunde","sequence":"additional","affiliation":[{"name":"Clemson University,Clemson,USA"}]},{"given":"Rhui Dih","family":"Lee","sequence":"additional","affiliation":[{"name":"IBM Research,Singapore"}]},{"given":"Achintya","family":"Kundu","sequence":"additional","affiliation":[{"name":"IBM Research,Singapore"}]},{"given":"Laura","family":"Wynter","sequence":"additional","affiliation":[{"name":"IBM Research,Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103514"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2021.3079202"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3202529"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3365440"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid51090.2021.00027"},{"article-title":"Towards gpu utilization prediction for cloud deep learning","volume-title":"Proceedings of the 12th USENIX Conference on Hot Topics in Cloud Computing, ser. HotCloud\u201920","author":"Yeung","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICFEC50348.2020.00016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3582080"},{"article-title":"Deep learning workload scheduling in gpu datacenters: Taxonomy, challenges and vision","year":"2022","author":"Gao","key":"ref9"},{"article-title":"A survey of multi-tenant deep learning inference on gpu","year":"2022","author":"Yu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EDGE60047.2023.00017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2991734"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2016.145"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2019.8927153"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","year":"2016","author":"Han","key":"ref17"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref18"},{"year":"2023","key":"ref19","article-title":"Edge tpu: Google\u2019s purpose-built asic designed to run inference at the edge"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00098"},{"year":"2023","key":"ref21","article-title":"Nvidia jetson xavier: A breakthrough in embedded applications"},{"year":"2023","key":"ref22","article-title":"Openvino toolkit: An open source toolkit that makes it easier to write once, deploy anywhere"},{"year":"2023","key":"ref23","article-title":"Jetpack sdk"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3089801.3089805"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref26","first-page":"295","article-title":"Mesos: A platform for fine-grained resource sharing in the data center","volume-title":"Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation, ser. NSDI\u201911","author":"H"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2499368.2451125"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E.2013.38"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"article-title":"Serving dnn models with multi-instance gpus: A case of the reconfigurable machine scheduling problem","year":"2021","author":"Tan","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/mtv.2009.19"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2435227.2435255"},{"article-title":"Energy minimization in dag scheduling on mpsocs at run-time: Theory and practice","year":"2019","author":"Simon","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2950251"},{"article-title":"Nimble: Lightweight and parallel gpu task scheduling for deep learning","year":"2020","author":"Kwon","key":"ref36"},{"article-title":"Autoware","year":"2023","author":"Foundation","key":"ref37"},{"year":"2023","key":"ref38","article-title":"Onnx runtime - cross-platform accelerated machine learning"},{"year":"2023","key":"ref39","article-title":"Tensor rt"},{"article-title":"Yolov3: An incremental improvement","year":"2018","author":"Redmon","key":"ref40"},{"article-title":"Yolox: Exceeding yolo series in 2021","year":"2021","author":"Ge","key":"ref41"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2019","author":"Devlin","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"A comprehensive overview of large language models","year":"2023","author":"Naveed","key":"ref44"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"T","key":"ref45"}],"event":{"name":"MILCOM 2023 - 2023 IEEE Military Communications Conference (MILCOM)","start":{"date-parts":[[2023,10,30]]},"location":"Boston, MA, USA","end":{"date-parts":[[2023,11,3]]}},"container-title":["MILCOM 2023 - 2023 IEEE Military Communications Conference (MILCOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10356123\/10356124\/10356363.pdf?arnumber=10356363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T20:29:08Z","timestamp":1705091348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10356363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,30]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/milcom58377.2023.10356363","relation":{},"subject":[],"published":{"date-parts":[[2023,10,30]]}}}