{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:54:12Z","timestamp":1764834852700,"version":"3.46.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,6]]},"DOI":"10.1109\/islped65674.2025.11261793","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:39:13Z","timestamp":1764787153000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["ECLIP: Energy-efficient and Practical Co-Location of ML Inference on Spatially Partitioned GPUs"],"prefix":"10.1109","author":[{"given":"Ryan","family":"Quach","sequence":"first","affiliation":[{"name":"University of California,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yidi","family":"Wang","sequence":"additional","affiliation":[{"name":"Santa Clara University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Jahanshahi","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Wong","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyoseung","family":"Kim","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3530390.3532735"},{"key":"ref2","first-page":"199","article-title":"Serving heterogeneous machine learning models on Multi-GPU servers with Spatio-Temporal sharing","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Choi"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3625549.3658654"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480063"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3634769.3634808"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/NAS51552.2021.9605434"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.3023723"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205311"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.29"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2016.14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071121"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1145\/3489517.3530510","article-title":"Paris and elsa: An elastic scheduling algorithm for reconfigurable multi-gpu inference servers","author":"Kim","year":"2022"},{"key":"ref15","article-title":"Amd gpu hardware basics"},{"key":"ref16","article-title":"AMD Graphics Core Next (GCN) Architecture"},{"key":"ref17","article-title":"Dissecting the polaris architecture"},{"key":"ref18","article-title":"Introducing AMD CDNA 2 Architecture"},{"key":"ref19","first-page":"10:1","article-title":"AMD GPUs as an Alternative to NVIDIA for Supporting Real-Time Workloads","volume-title":"32nd Euromicro Conference on Real-Time Systems (ECRTS 2020)","volume":"165","author":"Otterness"},{"key":"ref20","article-title":"Amd rocm documentation"},{"key":"ref21","article-title":"Heterogeneous system architecture runtime programmer\u2019s reference manual"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00042"},{"key":"ref23","first-page":"111","article-title":"Warped gates: Gating aware scheduling and power gating for gpgpus","volume-title":"Proceedings of the 46th Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Abdel-Majeed"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3634769.3634807"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS58335.2023.00012"},{"article-title":"Albert: A lite bert for self-supervised learning of language representations","year":"2020","author":"Lan","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3180270.3180271"},{"author":"Luo","key":"ref29","article-title":"Issue: Performance panelty caused by separated hsa queues in hip and openmp implementations"},{"key":"ref30","article-title":"Oversubscription of hardware resources in amd instinct accelerators"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3453417.3453432"},{"article-title":"Densely connected convolutional networks","year":"2018","author":"Huang","key":"ref32"},{"article-title":"One weird trick for parallelizing convolutional neural networks","year":"2014","author":"Krizhevsky","key":"ref33"},{"article-title":"Deep residual learning for image recognition","year":"2015","author":"He","key":"ref34"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.634","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2017"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01264-9_8","article-title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","author":"Ma","year":"2018"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2015","author":"Simonyan","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA.2019.8864564"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2477405"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037707"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446078"}],"event":{"name":"2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)","start":{"date-parts":[[2025,8,6]]},"location":"Reykjav\u00edk, Iceland","end":{"date-parts":[[2025,8,8]]}},"container-title":["2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11261694\/11261695\/11261793.pdf?arnumber=11261793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:49:56Z","timestamp":1764834596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11261793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/islped65674.2025.11261793","relation":{},"subject":[],"published":{"date-parts":[[2025,8,6]]}}}