{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:38:52Z","timestamp":1772933932359,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2211018,2116962,1955815"],"award-info":[{"award-number":["2211018,2116962,1955815"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402074","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"297-304","source":"Crossref","is-referenced-by-count":0,"title":["Dally: A Network-Placement Sensitive Cluster Scheduler for Deep Learning"],"prefix":"10.1109","author":[{"given":"Aakash","family":"Sharma","sequence":"first","affiliation":[{"name":"The Pennsylvania State University,Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivek M.","family":"Bhasi","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University,Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonali","family":"Singh","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University,Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahmut T.","family":"Kandemir","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University,Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Kesidis","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University,Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chita R.","family":"Das","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University,Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2022.3192720"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00039"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00047"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/bigdata62323.2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref6","article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","author":"Jeon","year":"2019","journal-title":"ATC. USENIX Association"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00023"},{"key":"ref12","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","author":"Gu","year":"2019","journal-title":"NSDI). USENIX Association"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126933"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1755913.1755940"},{"key":"ref17","article-title":"Themis: Fair and Efficient GPU Cluster Scheduling","author":"Mahajan","year":"2020","journal-title":"Proc. 17th USENIX NSDI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2019.2928289"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00033"},{"key":"ref24","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"Xiao","year":"2018","journal-title":"USENIX OSDI"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2007.06.028"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527382"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575705"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref33","author":"Won","year":"2023","journal-title":"ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"ref35","first-page":"945","article-title":"MLaaS in the Wild: Workload Analysis and Scheduling in \\{Large-Scale\\} Heterogeneous GPU Clusters","author":"Weng","year":"2022","journal-title":"Proc. USENIX NSDI"},{"key":"ref37","article-title":"AntMan: Dynamic scaling on GPU clusters for deep learning","author":"Xiao","year":"2020","journal-title":"Proc. OSDI. USENIX Association"},{"key":"ref38","article-title":"Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning","author":"Qiao","year":"2021","journal-title":"15th OSDI. USENIX Association"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052895"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/infocom42981.2021.9488916"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575721"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480859"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607054"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613175"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563464"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698560"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid51090.2021.00032"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486992"},{"key":"ref51","volume-title":"Gpu cluster scheduling for network-sensitive deep learning","author":"Sharma","year":"2024"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402074.pdf?arnumber=11402074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:55:35Z","timestamp":1772866535000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402074","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}