{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:13:31Z","timestamp":1781021611614,"version":"3.54.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"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":["61702494"],"award-info":[{"award-number":["61702494"]}],"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":["U1813203"],"award-info":[{"award-number":["U1813203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National High Technology Research and Development Program of China","award":["2015AA020109"],"award-info":[{"award-number":["2015AA020109"]}]},{"name":"National High Technology Research and Development Program of China","award":["2016YFB0201305"],"award-info":[{"award-number":["2016YFB0201305"]}]},{"name":"Shenzhen Fundamental Research Fund","award":["JCYJ20160331190123578"],"award-info":[{"award-number":["JCYJ20160331190123578"]}]},{"name":"Shenzhen Fundamental Research Fund","award":["GGFW2017073114031767"],"award-info":[{"award-number":["GGFW2017073114031767"]}]},{"name":"Shenzhen Discipline Construction Project for Urban Computing and Data Intelligence"},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2020,3,1]]},"DOI":"10.1109\/tpds.2019.2939785","type":"journal-article","created":{"date-parts":[[2019,9,6]],"date-time":"2019-09-06T19:45:24Z","timestamp":1567799124000},"page":"580-594","source":"Crossref","is-referenced-by-count":32,"title":["FeatherCNN: Fast Inference Computation with TensorGEMM on ARM Architectures"],"prefix":"10.1109","volume":"31","author":[{"given":"Haidong","family":"Lan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6208-4102","authenticated-orcid":false,"given":"Jintao","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Hundt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bertil","family":"Schmidt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minwen","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoning","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiguo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengzhong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Automatically tuned linear algebra software","author":"whaley","year":"1998","journal-title":"Proc 1998 ACM\/IEEE Supercomputing 98 Conf"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"ref33","article-title":"Pruning filters for efficient convnets","author":"li","year":"2016","journal-title":"arXiv preprint arXiv 1608 08710"},{"key":"ref32","first-page":"2849","article-title":"Fixed point quantization of deep convolutional networks","author":"lin","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"2365","DOI":"10.21437\/Interspeech.2013-552","article-title":"Restructuring of deep neural network acoustic models with singular value decomposition","author":"xue","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref30","first-page":"2013","article-title":"Darknet: Open source neural networks in c","author":"redmon","year":"0"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815993"},{"key":"ref36","first-page":"1337","article-title":"Deep learning with cots HPC systems","author":"coates","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","article-title":"Improving the speed of neural networks on cpus","volume":"1","author":"vanhoucke","year":"2011","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref34","article-title":"Flattened convolutional neural networks for feedforward acceleration","author":"jin","year":"2014","journal-title":"arXiv preprint arXiv 1412 5474"},{"key":"ref10","article-title":"Implementation of the basic linear algebra subprograms (blas)","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64203-1_37"},{"key":"ref11","article-title":"Fast convolutional nets with fbfft: A GPU performance evaluation","author":"vasilache","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref13","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv preprint arXiv 1704 04861"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref15","author":"cecka","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref17","article-title":"cuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014"},{"key":"ref18","year":"2018"},{"key":"ref19","first-page":"578","article-title":"TVM: An automated end-to-end optimization stack for deep learning","author":"chen","year":"2018","journal-title":"11th USENIX Symp Operating Syst Des Implementation"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref27","first-page":"730","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","article-title":"Top500","author":"dongarra","year":"2018"},{"key":"ref6","article-title":"Caffe2","year":"2017"},{"key":"ref29","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size","author":"iandola","year":"2016","journal-title":"arXiv preprint arXiv 1602 07360"},{"key":"ref5","article-title":"OpenBLAS library","author":"zhang","year":"2013"},{"key":"ref8","article-title":"The NNPACK library","author":"dukhan","year":"2015"},{"key":"ref7","article-title":"Eigen v3","author":"guennebaud","year":"2010"},{"key":"ref2","first-page":"199","article-title":"A 45nm 1.3 GHz 16.7 double-precision GFLOPS\/W RISC-V processor with vector accelerators","author":"lee","year":"2014","journal-title":"Proc Eur Solid State Circuits Conf"},{"key":"ref9","article-title":"Tensorflow lite","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref20","article-title":"TVM's benchmark results for several popular image classification models","author":"zheng","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3157733"},{"key":"ref22","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"1993","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref21","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41321-1_2"},{"key":"ref24","article-title":"Diversity networks: neural network compression using determinantal point processes","author":"mariet","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43659-3_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.31"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.05.302"},{"key":"ref26","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014567546"},{"key":"ref25","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8959349\/08826372.pdf?arnumber=8826372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T02:15:33Z","timestamp":1721700933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8826372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,1]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2019.2939785","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,1]]}}}