{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T07:04:00Z","timestamp":1765004640681,"version":"3.46.0"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JST SPRING","award":["JPMJSP2138"],"award-info":[{"award-number":["JPMJSP2138"]}]},{"name":"JSPS KAKENHI","award":["JP24K14914"],"award-info":[{"award-number":["JP24K14914"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tcc.2025.3626959","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:03:22Z","timestamp":1761847402000},"page":"1105-1118","source":"Crossref","is-referenced-by-count":0,"title":["Resource Aware Deep Learning Model Partitioning and Allocation for Inference Task in Clusters With Heterogeneous Graphics Processing Units"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1496-4377","authenticated-orcid":false,"given":"Akishige","family":"Ikoma","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, Osaka University, Suita, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9784-627X","authenticated-orcid":false,"given":"Yuichi","family":"Ohsita","sequence":"additional","affiliation":[{"name":"D3 Center, The University of Osaka, Toyonaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4168-2875","authenticated-orcid":false,"given":"Masayuki","family":"Murata","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Osaka, Suita, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep learning models for cloud, edge, fog, and IoT computing paradigms: Survey, recent advances, and future directions","volume-title":"Comput. Sci. Rev.","volume":"49","author":"Ahmad","year":"2023"},{"issue":"1","key":"ref2","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. 40th Int. Conf. Mach. Learn., Ser. Proc. Mach. Learn. Res.","volume":"202","author":"Dehghani","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-023-04104-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3136245"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624661"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2931558"},{"key":"ref8","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Huang","year":"2019"},{"key":"ref9","first-page":"663","article-title":"AlpaServe: Statistical multiplexing with model parallelism for deep learning serving","volume-title":"Proc. 17th USENIX Symp. Operating Syst. Des. Implementation","volume":"23","author":"Li","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DSD57027.2022.00048"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3399930"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3355010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icc.2011.5963442"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-1665-5_8"},{"year":"2023","key":"ref16","article-title":"Nvidia l4 tensor core GPU"},{"year":"2017","key":"ref17","article-title":"Nvidia v100 tensor core GPU"},{"year":"2021","key":"ref18","article-title":"Nvidia a30 tensor core GPU"},{"year":"2018","key":"ref19","article-title":"Nvidia t4"},{"year":"2022","key":"ref20","article-title":"Calient fs optical circuit switch"},{"key":"ref21","first-page":"26183","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","author":"Fang","year":"2021","journal-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst."},{"key":"ref22","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Tong","year":"2022"},{"article-title":"Qwen2.5 technical report","year":"2024","author":"Yang","key":"ref23"},{"article-title":"calflops: A FLOPs and params calculate tool for neural networks in PyTorch framework","year":"2023","author":"Ye","key":"ref24"},{"article-title":"Visual transformers: Token-based image representation and processing for computer vision","year":"2020","author":"Wu","key":"ref25"},{"article-title":"Gemma","year":"2024","author":"Team","key":"ref26"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6245519\/11278842\/11222947.pdf?arnumber=11222947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T06:59:06Z","timestamp":1765004346000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11222947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":26,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2025.3626959","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"type":"electronic","value":"2168-7161"},{"type":"electronic","value":"2372-0018"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}