{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T17:54:11Z","timestamp":1761587651103,"version":"build-2065373602"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T00:00:00Z","timestamp":1698624000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T00:00:00Z","timestamp":1698624000000},"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":[[2023,10,30]]},"DOI":"10.23919\/cnsm59352.2023.10327894","type":"proceedings-article","created":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T14:04:20Z","timestamp":1701180260000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Predicting the Performance of DNNs to Support Efficient Resource Allocation"],"prefix":"10.23919","author":[{"given":"Sarah","family":"Shah","sequence":"first","affiliation":[{"name":"University of Calgary,Electrical and Software Engineering,Calgary,Canada"}]},{"given":"Yasaman","family":"Amannejad","sequence":"additional","affiliation":[{"name":"Mount Royal University,Mathematics and Computing,Calgary,Canada"}]},{"given":"Diwakar","family":"Krishnamurthy","sequence":"additional","affiliation":[{"name":"University of Calgary,Electrical and Software Engineering,Calgary,Canada"}]}],"member":"263","reference":[{"volume-title":"The Top 10 Tech Trends In 2023 Everyone Must Be Ready For","key":"ref1"},{"volume-title":"Serving Models","key":"ref2"},{"volume-title":"Use containers to Build, Share and Run your applications","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2644658"},{"volume-title":"Runtime options with Memory, CPUs, and GPUs","key":"ref5"},{"key":"ref6","article-title":"Integer quantization for deep learning inference: Principles and empirical evaluation","author":"Wu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"On the use of ml for blackbox system performance prediction","author":"Fu","year":"2021","journal-title":"NSDI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2022.3223381"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155267"},{"key":"ref10","first-page":"5958","article-title":"Train big, then compress: Rethinking model size for efficient training and inference of transformers","volume-title":"International Conference on machine learning","author":"Li","year":"2020"},{"key":"ref11","article-title":"Fbgemm: Enabling high-performance low-precision deep learning inference","author":"Khudia","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486988"},{"journal-title":"Multi-model machine learning inference serving with gpu spatial partitioning","year":"2021","author":"Choi","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3066343"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005455"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3204975"},{"key":"ref18","article-title":"Serving dnns like clockwork: Performance predictability from the bottom up","author":"Gujarati","year":"2020","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2020.3006751"},{"issue":"3","key":"ref20","first-page":"31","article-title":"httperf-a tool for measuring web server performance","volume-title":"ACM SIGMETRICS Performance Evaluation Review","volume":"26","author":"Mosberger","year":"1998"},{"volume-title":"MNIST Dataset","key":"ref21"}],"event":{"name":"2023 19th International Conference on Network and Service Management (CNSM)","start":{"date-parts":[[2023,10,30]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2023,11,2]]}},"container-title":["2023 19th International Conference on Network and Service Management (CNSM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10327686\/10327788\/10327894.pdf?arnumber=10327894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T17:50:39Z","timestamp":1761587439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10327894\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,30]]},"references-count":21,"URL":"https:\/\/doi.org\/10.23919\/cnsm59352.2023.10327894","relation":{},"subject":[],"published":{"date-parts":[[2023,10,30]]}}}