{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T16:28:03Z","timestamp":1743784083499,"version":"3.37.3"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T00:00:00Z","timestamp":1663545600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T00:00:00Z","timestamp":1663545600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972444,61825202,62072195,61832006"],"award-info":[{"award-number":["61972444,61825202,62072195,61832006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,19]]},"DOI":"10.1109\/hpec55821.2022.9926290","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:40:48Z","timestamp":1667526048000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["Towards Fast GPU-based Sparse DNN Inference: A Hybrid Compute Model"],"prefix":"10.1109","author":[{"given":"Shaoxian","family":"Xu","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System\/Services Computing Technology, School of Computer Science and Technology, Huazhong University of Science and Technology,System Lab\/Cluster and Grid Computing Lab,Wuhan,China,430074"}]},{"given":"Minkang","family":"Wu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System\/Services Computing Technology, School of Computer Science and Technology, Huazhong University of Science and Technology,System Lab\/Cluster and Grid Computing Lab,Wuhan,China,430074"}]},{"given":"Long","family":"Zheng","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System\/Services Computing Technology, School of Computer Science and Technology, Huazhong University of Science and Technology,System Lab\/Cluster and Grid Computing Lab,Wuhan,China,430074"}]},{"given":"Zhiyuan","family":"Shao","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System\/Services Computing Technology, School of Computer Science and Technology, Huazhong University of Science and Technology,System Lab\/Cluster and Grid Computing Lab,Wuhan,China,430074"}]},{"given":"Xiangyu","family":"Ye","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System\/Services Computing Technology, School of Computer Science and Technology, Huazhong University of Science and Technology,System Lab\/Cluster and Grid Computing Lab,Wuhan,China,430074"}]},{"given":"Xiaofei","family":"Liao","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System\/Services Computing Technology, School of Computer Science and Technology, Huazhong University of Science and Technology,System Lab\/Cluster and Grid Computing Lab,Wuhan,China,430074"}]},{"given":"Hai","family":"Jin","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System\/Services Computing Technology, School of Computer Science and Technology, Huazhong University of Science and Technology,System Lab\/Cluster and Grid Computing Lab,Wuhan,China,430074"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2902","article-title":"Large-scale evolution of image classifiers","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML\u201917)","volume":"70","author":"Real"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00582"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2021.102152"},{"key":"ref4","first-page":"3360","article-title":"Exponential expressivity in deep neural networks through transient chaos","volume-title":"Proceedings of the 2016 Annual Conference on Neural Information Processing Systems (NIPS\u201916)","author":"Poole"},{"key":"ref5","first-page":"907","article-title":"The power of depth for feedforward neural networks","volume-title":"Proceedings of the 29th Conference on Learning Theory (COLT\u201916)","volume":"49","author":"Eldan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WI.2018.00-20"},{"key":"ref7","first-page":"1143","article-title":"Compressing neural networks using the variational information bottleneck","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML\u201918)","volume":"80","author":"Dai"},{"key":"ref8","article-title":"The state of sparsity in deep neural networks","volume":"abs\/1902.09574","author":"Gale","year":"2019","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916336"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286218"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286206"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622791"},{"volume-title":"NVIDIA. Nsight compute","key":"ref13"},{"volume-title":"Nvidia al00","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414654"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2019.00051"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508439"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2857721"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314646"},{"key":"ref21","article-title":"A survey of quantization methods for efficient neural network infer-ence","volume":"abs\/2103.13630","author":"Gholami","year":"2021","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2656893"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00016"},{"key":"ref24","first-page":"1","article-title":"Studying the effects of hashing of sparse deep neural networks on data and model parallelisms","volume-title":"Proceedings of 2020 IEEE High Performance Extreme Computing Conference (HPEC\u201920)","author":"Hasanzadeh-Mofrad"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.110"},{"volume-title":"NVIDIA. Concurrent kernel execution","key":"ref26"}],"event":{"name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2022,9,19]]},"location":"Waltham, MA, USA","end":{"date-parts":[[2022,9,23]]}},"container-title":["2022 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9926284\/9926287\/09926290.pdf?arnumber=9926290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T06:18:08Z","timestamp":1706077088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9926290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,19]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/hpec55821.2022.9926290","relation":{},"subject":[],"published":{"date-parts":[[2022,9,19]]}}}