{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T19:50:34Z","timestamp":1781466634639,"version":"3.54.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"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":["CNS-2003211,CNS-1939380"],"award-info":[{"award-number":["CNS-2003211,CNS-1939380"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,1]]},"DOI":"10.1109\/iccad51958.2021.9643501","type":"proceedings-article","created":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T23:06:46Z","timestamp":1640300806000},"page":"1-9","source":"Crossref","is-referenced-by-count":42,"title":["Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU"],"prefix":"10.1109","author":[{"given":"Fuxun","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shawn","family":"Bray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longfei","family":"Shangguan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xulong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenchen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Bisenet: Bilateral segmentation network for real-time semantic segmentation","author":"yu","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref11","author":"ren","year":"2015","journal-title":"Faster r-cnn Towards real-time object detection with region proposal networks"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2007.908582"},{"key":"ref13","year":"2020","journal-title":"Deep learning inference service at microsoft"},{"key":"ref14","year":"2020","journal-title":"Nvidia triron inference server"},{"key":"ref15","year":"2020","journal-title":"Nvidia a100 whitepaper"},{"key":"ref16","year":"2020","journal-title":"MPI for Python"},{"key":"ref17","year":"2020","journal-title":"Cuda-stream"},{"key":"ref18","first-page":"578","article-title":"{TVM}: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"13th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 18)"},{"key":"ref19","year":"2020","journal-title":"TensorFlow XLA (Accelerated Linear Algebra)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00936"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056383"},{"key":"ref2","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00164"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","year":"2020","journal-title":"Nvidia tensorrt"},{"key":"ref22","author":"yang","year":"2021","journal-title":"Equality saturation for tensor graph superoptimization"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"ref24","year":"2020","journal-title":"Cuda stream sync"},{"key":"ref23","author":"zhou","year":"2020","journal-title":"Transferable graph optimizers for ml compilers"},{"key":"ref26","author":"ding","year":"2020","journal-title":"Ios Inter-operator scheduler for cnn acceleration"},{"key":"ref25","year":"2020","journal-title":"Nvidia cudnn documentation"}],"event":{"name":"2021 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","location":"Munich, Germany","start":{"date-parts":[[2021,11,1]]},"end":{"date-parts":[[2021,11,4]]}},"container-title":["2021 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9643423\/9643432\/09643501.pdf?arnumber=9643501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:14Z","timestamp":1652201714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9643501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,1]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iccad51958.2021.9643501","relation":{},"subject":[],"published":{"date-parts":[[2021,11,1]]}}}