{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T14:25:26Z","timestamp":1775139926889,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T00:00:00Z","timestamp":1632096000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T00:00:00Z","timestamp":1632096000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T00:00:00Z","timestamp":1632096000000},"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,20]]},"DOI":"10.1109\/hpec49654.2021.9622791","type":"proceedings-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T20:57:36Z","timestamp":1638392256000},"page":"1-7","source":"Crossref","is-referenced-by-count":18,"title":["Fast Sparse Deep Neural Network Inference with Flexible SpMM Optimization Space Exploration"],"prefix":"10.1109","author":[{"given":"Jie","family":"Xin","sequence":"first","affiliation":[]},{"given":"Xianqi","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Long","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Qinggang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Pengcheng","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Linchen","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Xiaofei","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Hai","family":"Jin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"ref11","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2019.00051"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2016.7761646"},{"key":"ref16","article-title":"Cusparse library","author":"naumov","year":"0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916223"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286253"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916336"},{"key":"ref4","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proceedings of the 2015 International Conference on Learning Representations (ICLR)"},{"key":"ref3","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proceedings of the 2012 Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref8","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of the 2017 Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286218"},{"key":"ref9","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies (NAACL-HLT)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286206"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2738003"},{"key":"ref22","first-page":"1","article-title":"Studying the effects of hashing of sparse deep neural networks on data and model parallelisms","author":"hasanzadeh-mofrad","year":"2020","journal-title":"Proceedings of the 2020 IEEE High Performance Extreme Computing Conference (HPEC)"},{"key":"ref21","article-title":"How to access global memory efficiently in CUDA C\/C++ kernels","author":"harris","year":"2013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref23","first-page":"515","article-title":"GNNAdvisor: An adaptive and efficient runtime system for GNN acceleration on GPUs","author":"wang","year":"2021","journal-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI'02)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/331532.331562"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374546"}],"event":{"name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","location":"Waltham, MA, USA","start":{"date-parts":[[2021,9,20]]},"end":{"date-parts":[[2021,9,24]]}},"container-title":["2021 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9622740\/9622741\/09622791.pdf?arnumber=9622791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:53:48Z","timestamp":1652201628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9622791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,20]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/hpec49654.2021.9622791","relation":{},"subject":[],"published":{"date-parts":[[2021,9,20]]}}}