{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T01:08:09Z","timestamp":1780708089736,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2206522, 2319988"],"award-info":[{"award-number":["2206522, 2319988"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Commonwealth Cyber Initiative (CCI)"},{"name":"Microsoft Research Faculty Fellowship","award":["8300751"],"award-info":[{"award-number":["8300751"]}]},{"name":"FHWA","award":["693JJ31950016"],"award-info":[{"award-number":["693JJ31950016"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3689031.3696067","type":"proceedings-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:25:20Z","timestamp":1742970320000},"page":"507-523","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Flex: Fast, Accurate DNN Inference on Low-Cost Edges Using Heterogeneous Accelerator Execution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7677-3358","authenticated-orcid":false,"given":"Tanmoy","family":"Sen","sequence":"first","affiliation":[{"name":"University of Virginia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7548-6223","authenticated-orcid":false,"given":"Haiying","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Virginia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5952-3346","authenticated-orcid":false,"given":"Anand Padmanabha","family":"Iyer","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2021.102455"},{"key":"e_1_3_2_1_2_1","volume-title":"ACM Computing Surveys (CSUR)","author":"Cao Jacky","year":"2021","unstructured":"Jacky Cao, Kit-Yung Lam, Lik-Hang Lee, Xiaoli Liu, Pan Hui, and Xiang Su. Mobile augmented reality: User interfaces, frameworks, and intelligence. ACM Computing Surveys (CSUR), 2021."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809718"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2022.01.467"},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. of MobiCom","author":"Boateng George","year":"2019","unstructured":"George Boateng, Vivian Genaro Motti, Varun Mishra, John A Batsis, Josiah Hester, and David Kotz. Experience: Design, development and evaluation of a wearable device for mhealth applications. In Proc. of MobiCom, 2019."},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. of MobiCom","author":"Curtis Aidan","year":"2019","unstructured":"Aidan Curtis, Amruta Pai, Jian Cao, Nidal Moukaddam, and Ashutosh Sabharwal. Healthsense: Software-defined mobile-based clinical trials. In Proc. of MobiCom, 2019."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.22381\/ajmr91202210"},{"key":"e_1_3_2_1_8_1","volume-title":"Optimized mobile edge computing framework for iot based medical sensor network nodes. Journal of Ubiquitous Computing and Communication Technologies (UCCT), 3(01):33--42","author":"Raj Jennifer S","year":"2021","unstructured":"Jennifer S Raj and S Jennifer. Optimized mobile edge computing framework for iot based medical sensor network nodes. Journal of Ubiquitous Computing and Communication Technologies (UCCT), 3(01):33--42, 2021."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2000292"},{"key":"e_1_3_2_1_10_1","first-page":"23885","article-title":"Partial success in closing the gap between human and machine vision","volume":"34","author":"Geirhos Robert","year":"2021","unstructured":"Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Tizian Thieringer, Matthias Bethge, Felix A Wichmann, and Wieland Brendel. Partial success in closing the gap between human and machine vision. Advances in Neural Information Processing Systems, 34:23885--23899, 2021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Gunasekaran Jashwant Raj","year":"2022","unstructured":"Jashwant Raj Gunasekaran, Cyan Subhra Mishra, Prashanth Thinakaran, Bikash Sharma, Mahmut Taylan Kandemir, and Chita R. Das. Cocktail: A multidimensional optimization for model serving in cloud. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22), 2022."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87059-1_10"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICGI54032.2021.9655285"},{"key":"e_1_3_2_1_14_1","volume-title":"AWS Machine Learning Blog","author":"Zmnako Awrahman","year":"2022","unstructured":"Awrahman Zmnako, Tan Alan, Nadampalli Sunita, Hugo Jaramillo Velasquez Victor, and Liu Johna. Run machine learning inference workloads on AWS Graviton-based instances with Amazon SageMaker. AWS Machine Learning Blog, 2022. https:\/\/aws.amazon.com\/blogs\/machine-learning\/run-machine-learning-inference-workloads-on-aws-graviton-based-instances-with-amazon-sagemaker\/."},{"key":"e_1_3_2_1_15_1","volume-title":"https:\/\/www.gsma.com\/mobileeco nomy\/wp-content\/uploads\/2023\/03\/270223-The-Mobile-Economy-2023.pdf","author":"GSMA.","year":"2023","unstructured":"GSMA. The mobile economy 2023. https:\/\/www.gsma.com\/mobileeco nomy\/wp-content\/uploads\/2023\/03\/270223-The-Mobile-Economy-2023.pdf, 2023."},{"key":"e_1_3_2_1_16_1","unstructured":"ARM Community. Benchmarking floating-point precision in mobile gpus. https:\/\/community.arm.com\/arm-cornrnunity-blogs\/b\/graphics-gaming-and-vr-blog\/posts\/benchmarking-floating-point-precision-in-mobile-gpus. Accessed: 09-12-2022."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3412382.3458272"},{"key":"e_1_3_2_1_18_1","volume-title":"https:\/\/anonymous.4open.science\/r\/Elastically-Scheduling-Multiple-DNN-Inference-Jobs-on-an-Edge-Device-for-High-Efficiency-and-Accurac-B2FD\/README.md","author":"XX.","year":"2023","unstructured":"XX. FLEX. https:\/\/anonymous.4open.science\/r\/Elastically-Scheduling-Multiple-DNN-Inference-Jobs-on-an-Edge-Device-for-High-Efficiency-and-Accurac-B2FD\/README.md, 2023."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 2019 USENIX Conference on Usenix Annual Technical Conference","author":"Zhang Chengliang","year":"2019","unstructured":"Chengliang Zhang, Minchen Yu, Wei Wang, and Feng Yan. Mark: Exploiting cloud services for cost-effective, slo-aware machine learning inference serving. In Proceedings of the 2019 USENIX Conference on Usenix Annual Technical Conference, 2019."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_22_1","volume-title":"The European Symposium on Artificial Neural Networks","author":"Anguita D.","year":"2013","unstructured":"D. Anguita, Alessandro Ghio, L. Oneto, Xavier Parra, and Jorge Luis Reyes-Ortiz. A public domain dataset for human activity recognition using smartphones. In The European Symposium on Artificial Neural Networks, 2013."},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. of Usenix ATC","author":"Wan Cheng-Cheng","year":"2020","unstructured":"Cheng-Cheng Wan, M. Santriaji, E. Rogers, Henry Hoffmann, M. Maire, and Shanna Lu. Alert: Accurate anytime learning for energy and timeliness. Proc. of Usenix ATC, 2020."},{"key":"e_1_3_2_1_24_1","volume-title":"Native development kit","year":"2020","unstructured":"Android. Native development kit, 2020. https:\/\/developer.android.com\/ndk."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.4822753"},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. of MobiCom","author":"Fang Biyi","year":"2016","unstructured":"Biyi Fang, Xiao Zheng, and Mi Zhang. Nestdnn: Resource-aware multi-tenant on-device deep learning for continuous mobile vision. Proc. of MobiCom, 2016."},{"key":"e_1_3_2_1_27_1","unstructured":"Tensorflow model benchmark tool description. https:\/\/https:\/\/github.com\/tensorflow\/tensorflow\/tree\/master\/tensorflow\/tools\/benchmark. Accessed: 2020-4-27."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3274840"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_1_31_1","volume-title":"ICML","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, P. Abbeel, and Sergey Levine. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In ICML, 2018."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/AIKE.2018.00028"},{"key":"e_1_3_2_1_33_1","volume-title":"https:\/\/keras.io","author":"Keras Fran\u00e7ois Chollet","year":"2015","unstructured":"Fran\u00e7ois Chollet et al. Keras. https:\/\/keras.io, 2015."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_35_1","volume-title":"Grid search, random search, genetic algorithm: a big comparison for nas. arXiv preprint arXiv:1912.06059","author":"Liashchynskyi Petro","year":"2019","unstructured":"Petro Liashchynskyi and Pavlo Liashchynskyi. Grid search, random search, genetic algorithm: a big comparison for nas. arXiv preprint arXiv:1912.06059, 2019."},{"key":"e_1_3_2_1_36_1","unstructured":"Tomas Chladek. Profiler. https:\/\/play.google.com\/store\/apps\/details?id=cz.chladek.profiler&hl=en_US&gl=US."},{"key":"e_1_3_2_1_37_1","volume-title":"Cuda, release: 10.2.89","author":"P\u00e9ter Vingelmann NVIDIA","year":"2020","unstructured":"NVIDIA, P\u00e9ter Vingelmann, and Frank H.P. Fitzek. Cuda, release: 10.2.89, 2020."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"e_1_3_2_1_39_1","volume-title":"NSDI","author":"Guo Peizhen","year":"2021","unstructured":"Peizhen Guo, Bo Hu, and Wenjun Hu. Mistify: Automating dnn model porting for on-device inference at the edge. In NSDI, 2021."},{"key":"e_1_3_2_1_40_1","volume-title":"Proc. of ICLR","author":"Micikevicius Paulius","year":"2018","unstructured":"Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Frederick Diamos, Erich Elsen, David Garc\u00eda, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, and Hao Wu. Mixed precision training. Proc. of ICLR, 2018."},{"key":"e_1_3_2_1_41_1","volume-title":"https:\/\/play.google.com\/store\/apps\/details?id=com.digibites.accubattery&hl=en&gl=US&pli=1. &gl=US&pli=1. &pli=1. Online","year":"2023","unstructured":"Digibites. AccuBattery. https:\/\/play.google.com\/store\/apps\/details?id=com.digibites.accubattery&hl=en&gl=US&pli=1. &gl=US&pli=1. &pli=1. Online; accessed 11 January 2023."},{"key":"e_1_3_2_1_42_1","unstructured":"Emnist. http:\/\/cis.jhu.edu\/~sachin\/digit\/digit.html."},{"key":"e_1_3_2_1_43_1","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero, Qian Li, Neeraja J. Yadwadkar, and Christos Kozyrakis. INFaaS: Automated model-less inference serving. In 2021 USENIX Annual Technical Conference (USENIX ATC 21), 2021."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00095"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3195664"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386901.3388948"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2018.00028"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210337"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430716"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00038"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303950"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00061"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3431159"},{"key":"e_1_3_2_1_54_1","volume-title":"Slo-aware inference scheduler for heterogeneous processors in edge platforms. 18(4), jul","author":"Seo Wonik","year":"2021","unstructured":"Wonik Seo, Sanghoon Cha, Yeonjae Kim, Jaehyuk Huh, and Jongse Park. Slo-aware inference scheduler for heterogeneous processors in edge platforms. 18(4), jul 2021."},{"key":"e_1_3_2_1_55_1","volume-title":"Artificial Intelligence Review","author":"Solorio-Fern\u00e1ndez Sa\u00fal","year":"2021","unstructured":"Sa\u00fal Solorio-Fern\u00e1ndez, Jes\u00fas Ariel Carrasco-Ochoa, and Jos\u00e9 Francisco Mart\u00ednez Trinidad. A survey on feature selection methods for mixed data. Artificial Intelligence Review, 2021."},{"key":"e_1_3_2_1_56_1","unstructured":"The qualcomm snapdragon graphics pipeline explained. https:\/\/www.penguinsolutions.com\/about-us\/newsroom\/qualcomm-snapdragon-graphics-pipeline."}],"event":{"name":"EuroSys '25: Twentieth European Conference on Computer Systems","location":"Rotterdam Netherlands","acronym":"EuroSys '25","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Twentieth European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689031.3696067","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689031.3696067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T11:25:12Z","timestamp":1755775512000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689031.3696067"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":56,"alternative-id":["10.1145\/3689031.3696067","10.1145\/3689031"],"URL":"https:\/\/doi.org\/10.1145\/3689031.3696067","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}