{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:46:16Z","timestamp":1772725576559,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["2022YFB4501404"],"award-info":[{"award-number":["2022YFB4501404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4232036"],"award-info":[{"award-number":["4232036"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,25]]},"DOI":"10.1109\/hpec58863.2023.10363545","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:39:57Z","timestamp":1703533197000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["Adaptive Sparse Deep Neural Network Inference on Resource-Constrained Cost-Efficient GPUs"],"prefix":"10.1109","author":[{"given":"Ming","family":"Dun","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Lab of Processors,Beijing,China"}]},{"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Lab of Processors,Beijing,China"}]},{"given":"Huawei","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Lab of Processors,Beijing,China"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Lab of Processors,Beijing,China"}]},{"given":"Junying","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Lab of Processors,Beijing,China"}]},{"given":"Xiaochun","family":"Ye","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Lab of Processors,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073592"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106617"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref4","first-page":"1877","article-title":"Language mod-els are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.60"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180220"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324920000601"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916336"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2019.00051"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622791"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286206"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286218"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926300"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3011893"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926290"},{"key":"ref17","first-page":"551","article-title":"Zero-offload: Democratizing billion-scale model training","volume-title":"USENIX Annual Technical Conference","author":"Ren"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"ref19","first-page":"1","article-title":"Measuring the effects of data parallelism on neural network training","volume":"20","author":"Shallue","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00064"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref22","volume-title":"Nvidia turing architecture whitepaper","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3331057"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3210377.3210394"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530508"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF01586000"}],"event":{"name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","location":"Boston, MA, USA","start":{"date-parts":[[2023,9,25]]},"end":{"date-parts":[[2023,9,29]]}},"container-title":["2023 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10363430\/10363422\/10363545.pdf?arnumber=10363545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T20:35:16Z","timestamp":1705091716000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10363545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,25]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/hpec58863.2023.10363545","relation":{},"subject":[],"published":{"date-parts":[[2023,9,25]]}}}