{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T09:33:13Z","timestamp":1785576793578,"version":"3.56.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2019B010155002"],"award-info":[{"award-number":["2019B010155002"]}]},{"name":"PKU-Baidu Fund","award":["2020BD024"],"award-info":[{"award-number":["2020BD024"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1109\/tcad.2021.3108065","type":"journal-article","created":{"date-parts":[[2021,8,26]],"date-time":"2021-08-26T20:31:35Z","timestamp":1630009895000},"page":"2546-2559","source":"Crossref","is-referenced-by-count":17,"title":["FCNNLib: A Flexible Convolution Algorithm Library for Deep Learning on FPGAs"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9076-7998","authenticated-orcid":false,"given":"Yun","family":"Liang","sequence":"first","affiliation":[{"name":"Center for Energy-Efficient Computing and Applications, School of EECS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6230-5342","authenticated-orcid":false,"given":"Qingcheng","family":"Xiao","sequence":"additional","affiliation":[{"name":"Center for Energy-Efficient Computing and Applications, School of EECS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3801-6847","authenticated-orcid":false,"given":"Liqiang","family":"Lu","sequence":"additional","affiliation":[{"name":"Center for Energy-Efficient Computing and Applications, School of EECS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Xie","sequence":"additional","affiliation":[{"name":"Center for Energy-Efficient Computing and Applications, School of EECS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304058"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080228"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.20"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174253"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330384"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205324"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208062"},{"key":"ref53","year":"2019","journal-title":"Xilinx Power Estimator"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847276"},{"key":"ref11","article-title":"An efficient hardware design for accelerating sparse CNNs with NAS-based models","author":"liang","year":"2021","journal-title":"IEEE Trans Comput -Aided Design Integr Circuits Syst"},{"key":"ref55","year":"2019","journal-title":"AMD MIOpen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3023903"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.25"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2019.00013"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293947"},{"key":"ref19","year":"2019","journal-title":"Nvidia cuDNN"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021727"},{"key":"ref50","year":"2021","journal-title":"Xilinx Power Estimator"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415609"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.vlsi.2017.12.009"},{"key":"ref48","year":"2021","journal-title":"Convolutional neural network"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2785257"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102363"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.64"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062244"},{"key":"ref49","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00062"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.032271058"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2821561"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3DIC.2016.7970018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174265"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465915"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783722"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050344"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240856"},{"key":"ref33","first-page":"1","article-title":"DNNWEAVER: From high-level deep network models to FPGA acceleration","author":"sharma","year":"2016","journal-title":"Proc Workshop Cogn Archit"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218748"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293904"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref38","first-page":"168","article-title":"Embedded binarized neural networks","author":"mcdanel","year":"2017","journal-title":"Proc Int Conf Embedded Wireless Syst Netw"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-018-0604-8"},{"key":"ref24","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Conf Oper Syst Design Implement"},{"key":"ref68","author":"istrate","year":"2018","journal-title":"Incremental training of deep convolutional neural networks"},{"key":"ref23","year":"2019","journal-title":"Intel MKL-DNN"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314628"},{"key":"ref26","year":"2019","journal-title":"Intel FPGA SDK for OpenCL"},{"key":"ref25","first-page":"1","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196079"},{"key":"ref20","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661185"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00034"},{"key":"ref22","year":"2019","journal-title":"ARM Computer Library"},{"key":"ref66","first-page":"145","article-title":"Synchronous multi-GPU training for deep learning with low-precision communications: An empirical study","author":"grubic","year":"2018","journal-title":"Proc EDBT"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3199605"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00030"},{"key":"ref27","year":"2019","journal-title":"Xilinx Vivado High-level Synthesis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2844093"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00138"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303949"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2692916.2555255"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/9832686\/09523575.pdf?arnumber=9523575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T22:12:51Z","timestamp":1697494371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9523575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8]]},"references-count":70,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2021.3108065","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8]]}}}