{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T22:52:07Z","timestamp":1776725527686,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11132423","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["DARIS: An Oversubscribed Spatio-Temporal Scheduler for Real-Time DNN Inference on GPUs"],"prefix":"10.1109","author":[{"given":"Amir Fakhim","family":"Babaei","sequence":"first","affiliation":[{"name":"Virginia Tech Arlington,Department of Electrical & Computer Engineering,Virginia,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thidapat","family":"Chantem","sequence":"additional","affiliation":[{"name":"Virginia Tech Arlington,Department of Electrical & Computer Engineering,Virginia,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460371"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3442442.3452055"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3638757"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00034"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108305"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICEE59167.2023.10334772"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2023.109577"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS59052.2023.00023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/QICAR61538.2024.10496604"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2023.102901"},{"key":"ref12","article-title":"A survey of multi-tenant deep learning inference on gpu","author":"Yu","year":"2022","journal-title":"arXiv preprint arXiv:2203.09040"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330351"},{"key":"ref14","first-page":"443","article-title":"Serving {dnns} like clockwork: Performance predictability from the bottom up","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Gujarati"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546669"},{"key":"ref17","volume-title":"NVIDIA Multi-Process Service Documentation"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3528535.3565247"},{"key":"ref19","article-title":"D-stack: High throughput dnn inference by effective multiplexing and spatio-temporal scheduling of gpus","author":"Dhakal","year":"2023","journal-title":"arXiv preprint arXiv:2304.13541"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD60044.2023.00014"},{"key":"ref21","first-page":"539","article-title":"Microsecond-scale preemption for concurrent {gpu-accelerated}{dnn} inferences","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Han"},{"key":"ref22","first-page":"499","article-title":"{Pipeswitch}: Fast pipelined context switching for deep learning applications","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Bai"},{"key":"ref23","first-page":"787","article-title":"{Shepherd}: Serving {dnns} in the wild","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Zhang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3631311.3632401"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3235439"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11132423.pdf?arnumber=11132423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:36:00Z","timestamp":1758000960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132423","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}