{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:54:40Z","timestamp":1781675680082,"version":"3.54.5"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,11]]},"DOI":"10.1109\/rtas68450.2026.00030","type":"proceedings-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:42:26Z","timestamp":1781638946000},"page":"234-246","source":"Crossref","is-referenced-by-count":0,"title":["ZeroSwap: Minimizing Swap Overhead for Real-Time Multi-DNN Inference via SSD-based GPU Memory Extension"],"prefix":"10.1109","author":[{"given":"Woosung","family":"Kang","sequence":"first","affiliation":[{"name":"Daegu Gyeongbuk Institute of Science and Technology (DGIST),Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Filippo","family":"Muzzini","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianluca","family":"Brilli","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong-Chan","family":"Kim","sequence":"additional","affiliation":[{"name":"Kookmin University,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinkyu","family":"Lee","sequence":"additional","affiliation":[{"name":"Yonsei University,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hoon Sung","family":"Chwa","sequence":"additional","affiliation":[{"name":"Daegu Gyeongbuk Institute of Science and Technology (DGIST),Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref2","article-title":"Bev-former: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers","volume-title":"ECCV","author":"Li"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref4","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"ICML","author":"Xiao"},{"key":"ref5","article-title":"Rethinking the value of network pruning","volume-title":"ICLR","author":"Liu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref8","article-title":"Gdev: First-class GPU resource management in the operating system","volume-title":"ATC","author":"Kato"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2817817.2731192"},{"key":"ref10","article-title":"Fine-grained gpu sharing primitives for deep learning applications","author":"Yu","year":"2020","journal-title":"MLSys"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378530"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00057"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS61025.2024.00037"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00039"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00033"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD49847.2020.00036"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00090"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/NVMSA53655.2021.9628829"},{"key":"ref21","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"NIPS","author":"Paszke"},{"key":"ref22","volume-title":"NVIDIA Jetson Orin Nano Super DevKit"},{"key":"ref23","volume-title":"SK hynix Platinum P41 SSD"},{"key":"ref24","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"NIPS","author":"Ren"},{"key":"ref26","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"ICML","author":"Tan"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS48715.2020.00007"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6018"},{"key":"ref29","article-title":"PyTorch Documentation: CUDA Memory Management"},{"key":"ref30","article-title":"BFC (Best-Fit with Coalescing) Allocator Implementation","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/REAL.1990.128747"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS54340.2022.00021"},{"key":"ref33","article-title":"Gurobi Optimizer Reference Manual","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11241-005-0507-9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"}],"event":{"name":"2026 IEEE 32nd Real-Time and Embedded Technology and Applications Symposium (RTAS)","location":"Saint Malo, France","start":{"date-parts":[[2026,5,11]]},"end":{"date-parts":[[2026,5,14]]}},"container-title":["2026 IEEE 32nd Real-Time and Embedded Technology and Applications Symposium (RTAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11558268\/11558364\/11558382.pdf?arnumber=11558382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:22:07Z","timestamp":1781673727000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11558382\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/rtas68450.2026.00030","relation":{},"subject":[],"published":{"date-parts":[[2026,5,11]]}}}