{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T19:42:32Z","timestamp":1773776552144,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/ccgrid64434.2025.00015","type":"proceedings-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T17:36:08Z","timestamp":1751304968000},"page":"43-52","source":"Crossref","is-referenced-by-count":2,"title":["Power- and Fragmentation-Aware Online Scheduling for GPU Datacenters"],"prefix":"10.1109","author":[{"given":"Francesco","family":"Lettich","sequence":"first","affiliation":[{"name":"Istituto di Scienza e Tecnologie dell'Informazione “Alessandro Faedo”, Consiglio Nazionale delle Ricerche,Pisa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuele","family":"Carlini","sequence":"additional","affiliation":[{"name":"Istituto di Scienza e Tecnologie dell'Informazione “Alessandro Faedo”, Consiglio Nazionale delle Ricerche,Pisa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franco Maria","family":"Nardini","sequence":"additional","affiliation":[{"name":"Istituto di Scienza e Tecnologie dell'Informazione “Alessandro Faedo”, Consiglio Nazionale delle Ricerche,Pisa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raffaele","family":"Perego","sequence":"additional","affiliation":[{"name":"Istituto di Scienza e Tecnologie dell'Informazione “Alessandro Faedo”, Consiglio Nazionale delle Ricerche,Pisa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salvatore","family":"Trani","sequence":"additional","affiliation":[{"name":"Istituto di Scienza e Tecnologie dell'Informazione “Alessandro Faedo”, Consiglio Nazionale delle Ricerche,Pisa,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533234"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/FiCloud49777.2021.00063"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps47924.2020.00084"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2024.3470074"},{"key":"ref6","first-page":"845","author":"Hadary","year":"2020","journal-title":"Protean: VM allocation service at scale. In 14th USENIX OSDI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/en16020890"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5437"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tc.2017.2742513"},{"issue":"2","key":"ref11","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/LCA.2023.3278652","volume":"22","author":"Patel","year":"2023","journal-title":"Towards improved power management in cloud GPUs. IEEE Computer Architecture Letters"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2021.111787"},{"issue":"2","key":"ref13","first-page":"19","volume":"3","author":"Andrae","year":"2020","journal-title":"New perspectives on internet electricity use in2030. Engineering and Applied Science Letter"},{"key":"ref14","author":"Snell","year":"2024","journal-title":"Scaling LLM test-time compute optimally can be more effective than scaling model parameters"},{"key":"ref15","first-page":"53418","volume":"11","author":"Tai","year":"2023","journal-title":"An integrated optimization-based algorithm for energy efficiency and resource allocation in heterogeneous cloud computing centers. IEEE Access"},{"key":"ref16","author":"Wei","year":"2022","journal-title":"Emergent abilities of large language models"},{"key":"ref17","first-page":"945","author":"Weng","year":"2022","journal-title":"MLaaS in the wild: Workload analysis and scheduling in Large-Scale heterogeneous GPU clusters. In 19th USENIX NSDI"},{"key":"ref18","first-page":"995","author":"Weng","year":"2023","journal-title":"Beware of fragmentation: Scheduling GPU-sharing workloads with fragmentation gradient descent. In USENIX ATC"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2013.06.009"},{"key":"ref20","first-page":"595","author":"Xiao","year":"2018","journal-title":"Gandiva: Introspective cluster scheduling for deep learning. In 13th USENIX OSDI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3638757"}],"event":{"name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","location":"Troms\u00f8, Norway","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,22]]}},"container-title":["2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11044421\/11044790\/11044800.pdf?arnumber=11044800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T06:02:40Z","timestamp":1751349760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11044800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ccgrid64434.2025.00015","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}