{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T02:38:00Z","timestamp":1779935880088,"version":"3.53.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2021ZD0110104"],"award-info":[{"award-number":["2021ZD0110104"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222210"],"award-info":[{"award-number":["62222210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2017"],"award-info":[{"award-number":["U21B2017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072297"],"award-info":[{"award-number":["62072297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tc.2024.3365942","type":"journal-article","created":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T18:39:43Z","timestamp":1707935983000},"page":"1275-1289","source":"Crossref","is-referenced-by-count":17,"title":["Accelerating Sparse DNNs Based on Tiled GEMM"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4479-5525","authenticated-orcid":false,"given":"Cong","family":"Guo","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6080-5703","authenticated-orcid":false,"given":"Fengchen","family":"Xue","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5660-5493","authenticated-orcid":false,"given":"Jingwen","family":"Leng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4040-0159","authenticated-orcid":false,"given":"Yuxian","family":"Qiu","sequence":"additional","affiliation":[{"name":"NVIDIA, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7433-2627","authenticated-orcid":false,"given":"Yue","family":"Guan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6646-5260","authenticated-orcid":false,"given":"Weihao","family":"Cui","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5832-0347","authenticated-orcid":false,"given":"Quan","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2302","authenticated-orcid":false,"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"6 areas where artificial neural networks outperform humans","author":"Steinberg","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref4","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han","year":"2015"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1145\/3123939.3123970","article-title":"DeftNN: Addressing bottlenecks for DNN execution on GPUs via synapse vector elimination and near-compute data fission","volume-title":"Proc. 50th Annu. IEEE\/ACM Int. Symp. Microarchit.","author":"Hill","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015676"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"key":"ref9","article-title":"Nvidia a100 tensor core architecture","year":"2020"},{"key":"ref10","first-page":"1","article-title":"High performance convolutional neural networks for document processing","volume-title":"Proc. 10th Int. Workshop Frontiers Handwriting Recognit.","author":"Chellapilla","year":"2006"},{"key":"ref11","article-title":"NVIDIA Volta GPU architecture white paper","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218732"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref15","article-title":"cuDNN: Efficient primitives for deep learning","author":"Chetlur","year":"2014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC53511.2021.00029"},{"key":"ref17","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn., (PMLR)","author":"Gupta","year":"2015"},{"key":"ref18","first-page":"7197","article-title":"Up or down? Adaptive rounding for post-training quantization","volume-title":"Proc. Int. Conf. Mach. Learn., (PMLR)","author":"Nagel","year":"2020"},{"key":"ref19","article-title":"Squant: On-the-fly data-free quantization via diagonal hessian approximation","author":"Guo","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00095"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref22","article-title":"CUDA toolkit documentation v10.1","year":"2019"},{"key":"ref23","article-title":"CUTLASS 1.3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476138"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530585"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00042"},{"key":"ref27","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen","year":"2016"},{"key":"ref28","article-title":"Block-sparse recurrent neural networks","author":"Narang","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00020"},{"key":"ref30","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref32","article-title":"GPU Pro Tip: CUDA 7 streams simplify concurrency","author":"Harris","year":"2015"},{"key":"ref33","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Simonyan","year":"2015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref36","article-title":"Neural machine translation (seq2seq) tutorial","author":"Luong","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1100"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref41","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref42","volume-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"(2015)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195774"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"ref45","article-title":"Integer quantization for deep learning inference: Principles and empirical evaluation","author":"Wu","year":"2020"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/10494819\/10436533.pdf?arnumber=10436533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T18:09:58Z","timestamp":1725559798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10436533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":45,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tc.2024.3365942","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}