{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T05:05:34Z","timestamp":1734239134048,"version":"3.30.2"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1109\/mascots64422.2024.10786549","type":"proceedings-article","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T18:50:09Z","timestamp":1734115809000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Cloud Reamer: Enabling Inference Services in Training Clusters"],"prefix":"10.1109","author":[{"given":"Osama","family":"Khan","sequence":"first","affiliation":[{"name":"Sungkyunkwan University,Suwon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gwanjong","family":"Park","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University,Suwon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyeol","family":"Yu","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University,Suwon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Euiseong","family":"Seo","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University,Suwon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"853","article-title":"CODA: Improving resource utilization by slimming and colocating DNN and CPU jobs","volume-title":"Proceedings of the IEEE International Conference on Distributed Computing Systems","author":"Zhao"},{"key":"ref2","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","volume-title":"Proceedings of the USENIX Annual Technical Conference","author":"Jeon"},{"key":"ref3","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters","volume-title":"Proceedings of the USENIX Symposium on Networked Systems Design and Implementation","author":"Weng"},{"volume-title":"NVIDIA","key":"ref4","article-title":"NVIDIA-Certified Systems Configuration Guide for PCIe Servers"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3303988"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref7","article-title":"Optimize Inference"},{"key":"ref8","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref11","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref12","article-title":"Deep Speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv preprint arXiv:1412.5567"},{"key":"ref13","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proceedings of the USENIX Symposium on Networked Systems Design and Implementation","author":"Gu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"ref15","first-page":"1025","article-title":"Optimizing CNN model inference on CPUs","volume-title":"Proceedings of the USENIX Annual Technical Conference","author":"Liu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3269530"},{"volume-title":"Scheduling Frameworks","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2013.19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21395-3_7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00036"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448625"}],"event":{"name":"2024 32nd International Conference on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)","start":{"date-parts":[[2024,10,21]]},"location":"Krakow, Poland","end":{"date-parts":[[2024,10,23]]}},"container-title":["2024 32nd International Conference on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10786488\/10786336\/10786549.pdf?arnumber=10786549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T06:53:20Z","timestamp":1734159200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10786549\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/mascots64422.2024.10786549","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]}}}