{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T18:12:04Z","timestamp":1760724724831,"version":"build-2065373602"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,15]]},"DOI":"10.1109\/hpec67600.2025.11196684","type":"proceedings-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:35:37Z","timestamp":1760636137000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Towards Efficient Sparse Deep Neural Network Inference via Multi-level Concurrency Orchestration"],"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":"Jie","family":"Zhou","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":"Shuhan","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Lab of Processors,Beijing,China"}]},{"given":"Yiming","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,State Key Lab of Processors,Beijing,China"}]},{"given":"Mingyu","family":"Yan","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":"10.1109\/ICME46284.2020.9102768"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359658"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1142\/S0218339019500013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05594-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2014.51"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"article-title":"Deepseek llm: Scaling open-source language models with longtermism","year":"2024","author":"Bi","key":"ref7"},{"issue":"241","key":"ref8","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3685277"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717481"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916336"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2019.00051"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622791"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286206"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926300"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363545"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00044"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563510"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3464298.3493391"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616672"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715996"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CGO53902.2022.9741270"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638470"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3695466"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673108"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070957"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2013.6799112"}],"event":{"name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2025,9,15]]},"location":"Wakefield, MA, USA","end":{"date-parts":[[2025,9,19]]}},"container-title":["2025 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11196085\/11196088\/11196684.pdf?arnumber=11196684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:38:32Z","timestamp":1760722712000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11196684\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/hpec67600.2025.11196684","relation":{},"subject":[],"published":{"date-parts":[[2025,9,15]]}}}