{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:14:46Z","timestamp":1771697686018,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T00:00:00Z","timestamp":1614124800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Samsung Research Funding & Incubation Center for Future Technology","award":["SRFC-IT1901-15"],"award-info":[{"award-number":["SRFC-IT1901-15"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,2,24]]},"DOI":"10.1145\/3446382.3448606","type":"proceedings-article","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T23:51:00Z","timestamp":1613865060000},"page":"57-63","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs"],"prefix":"10.1145","author":[{"given":"Sumin","family":"Kim","sequence":"first","affiliation":[{"name":"University of Seoul"}]},{"given":"Seunghwan","family":"Oh","sequence":"additional","affiliation":[{"name":"University of Seoul"}]},{"given":"Youngmin","family":"Yi","sequence":"additional","affiliation":[{"name":"University of Seoul"}]}],"member":"320","published-online":{"date-parts":[[2021,2,24]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Andrei Frumusanu. 2019. Galaxy Note10+- Full phone specifications. https:\/\/www.gsmarena.com\/samsung_galaxy_note10+-9732.php.  Andrei Frumusanu. 2019. Galaxy Note10+- Full phone specifications. https:\/\/www.gsmarena.com\/samsung_galaxy_note10+-9732.php."},{"key":"e_1_3_2_1_2_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard , Menglong Zhu , Bo Chen , Dmitry Kalenichenko , Weijun Wang , Tobias Weyand , Marco Andreetto , and Hartwig Adam . 2017 . Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017). Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_3_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and&lt","author":"Iandola Forrest N","year":"2016","unstructured":"Forrest N Iandola , Song Han , Matthew W Moskewicz , Khalid Ashraf , William J Dally , and Kurt Keutzer . 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and&lt ; 0.5 MB model size. arXiv preprint arXiv:1602.07360 ( 2016 ). Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Andrey Ignatov Radu Timofte William Chou Ke Wang Max Wu Tim Hartley and Luc Van Gool. 2018. Ai benchmark: Running deep neural networks on android smartphones. In ECCV. 0--0.  Andrey Ignatov Radu Timofte William Chou Ke Wang Max Wu Tim Hartley and Luc Van Gool. 2018. Ai benchmark: Running deep neural networks on android smartphones. In ECCV. 0--0.","DOI":"10.1007\/978-3-030-11021-5_19"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Benoit Jacob Skirmantas Kligys Bo Chen Menglong Zhu Matthew Tang Andrew Howard Hartwig Adam and Dmitry Kalenichenko. 2018. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In CVPR. 2704--2713.  Benoit Jacob Skirmantas Kligys Bo Chen Menglong Zhu Matthew Tang Andrew Howard Hartwig Adam and Dmitry Kalenichenko. 2018. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In CVPR. 2704--2713.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_6_1","unstructured":"Khronos\u00ae OpenCL Working Group. 2020. The OpenCLTM Specification. https:\/\/www.khronos.org\/registry\/OpenCL\/specs\/3.0-unified\/pdf\/OpenCL_API.pdf.  Khronos\u00ae OpenCL Working Group. 2020. The OpenCLTM Specification. https:\/\/www.khronos.org\/registry\/OpenCL\/specs\/3.0-unified\/pdf\/OpenCL_API.pdf."},{"key":"e_1_3_2_1_7_1","volume-title":"Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710","author":"Li Hao","year":"2016","unstructured":"Hao Li , Asim Kadav , Igor Durdanovic , Hanan Samet , and Hans Peter Graf . 2016. Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 ( 2016 ). Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2016. Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372799.3394366"},{"key":"e_1_3_2_1_9_1","unstructured":"Qualcomm Technologies Inc. 2019. Snapdragon 865 Mobile Hardware Development Kit. developer.qualcomm.com\/hardware\/snapdragon-865-hdk.  Qualcomm Technologies Inc. 2019. Snapdragon 865 Mobile Hardware Development Kit. developer.qualcomm.com\/hardware\/snapdragon-865-hdk."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2020.2968258"},{"key":"e_1_3_2_1_11_1","unstructured":"Lingqi Zhang Mohamed Wahib and Satoshi Matsuoka. 2019. Understanding the Overheads of Launching CUDA Kernels. In ICPP19.  Lingqi Zhang Mohamed Wahib and Satoshi Matsuoka. 2019. Understanding the Overheads of Launching CUDA Kernels. In ICPP19."}],"event":{"name":"HotMobile '21: The 22nd International Workshop on Mobile Computing Systems and Applications","location":"Virtual United Kingdom","acronym":"HotMobile '21","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3446382.3448606","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3446382.3448606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:27Z","timestamp":1750191447000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3446382.3448606"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,24]]},"references-count":11,"alternative-id":["10.1145\/3446382.3448606","10.1145\/3446382"],"URL":"https:\/\/doi.org\/10.1145\/3446382.3448606","relation":{},"subject":[],"published":{"date-parts":[[2021,2,24]]},"assertion":[{"value":"2021-02-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}