{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:32:39Z","timestamp":1749184359665,"version":"3.37.3"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T00:00:00Z","timestamp":1670112000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T00:00:00Z","timestamp":1670112000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001807","name":"NSF of China","doi-asserted-by":"publisher","award":["61972171,62172375"],"award-info":[{"award-number":["61972171,62172375"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,4]]},"DOI":"10.1109\/globecom48099.2022.10001581","type":"proceedings-article","created":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T22:24:18Z","timestamp":1673475858000},"page":"2242-2247","source":"Crossref","is-referenced-by-count":3,"title":["Performance Efficient Layer-aware DNN Inference Task Scheduling in GPU Cluster"],"prefix":"10.1109","author":[{"given":"Hongmin","family":"Geng","sequence":"first","affiliation":[{"name":"School of Computer Science, China University of Geosciences,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deze","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer Science, China University of Geosciences,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuepeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, China University of Geosciences,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1038\/nature14539"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/s11263-015-0816-y"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR.2014.81"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1145\/2906388.2906396"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICPP.2016.15"},{"key":"ref6","article-title":"The 000 VLIW JIT compiler for GPU inference","volume":"abs\/1901.10008","author":"Jain","year":"2019","journal-title":"CoRR"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Switch transform-ers: Scaling to trillion parameter models with simple and efficient sparsity","author":"Fedus","year":"2021","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Model compression with adversarial robustness: A unified optimization framework","volume":"32","author":"Gui","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TIP.2019.2941660"},{"key":"ref11","first-page":"1","article-title":"Improving device-edge cooperative inference of deep learning via 2-step pruning","volume-title":"Proceedings of the IEEE International Conference on Computer Communications (INFO COM)","author":"Shi","year":"2019"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.24963\/ijcai.2018\/318"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TWC.2019.2946140"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TPDS.2020.3041474"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/INFOCOM.2019.8737614"},{"key":"ref16","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1038\/nature16961"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/IWQOS52092.2021.9521304"}],"event":{"name":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","start":{"date-parts":[[2022,12,4]]},"location":"Rio de Janeiro, Brazil","end":{"date-parts":[[2022,12,8]]}},"container-title":["GLOBECOM 2022 - 2022 IEEE Global Communications Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10000063\/10000593\/10001581.pdf?arnumber=10001581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T23:24:35Z","timestamp":1710372275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10001581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/globecom48099.2022.10001581","relation":{},"subject":[],"published":{"date-parts":[[2022,12,4]]}}}