{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:56:05Z","timestamp":1771959365303,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018YFB0204403"],"award-info":[{"award-number":["2018YFB0204403"]}]},{"name":"Strategic Priority CAS","award":["XDB38050100"],"award-info":[{"award-number":["XDB38050100"]}]},{"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":"Shenzhen Basic Research Fund","award":["RCYX2020071411473419"],"award-info":[{"award-number":["RCYX2020071411473419"]}]},{"name":"Shenzhen Basic Research Fund","award":["KQTD20200820113106007"],"award-info":[{"award-number":["KQTD20200820113106007"]}]},{"name":"Shenzhen Basic Research Fund","award":["JSGG20190220164202211"],"award-info":[{"award-number":["JSGG20190220164202211"]}]},{"name":"CAS Key Lab","award":["2011DP173015"],"award-info":[{"award-number":["2011DP173015"]}]},{"name":"JST, PRESTO","award":["JPMJPR20MA"],"award-info":[{"award-number":["JPMJPR20MA"]}]},{"name":"JSPS KAKENHI","award":["JP21K17750"],"award-info":[{"award-number":["JP21K17750"]}]},{"name":"AIST Emerging Research, Japan","award":["AAZ2029701B"],"award-info":[{"award-number":["AAZ2029701B"]}]},{"name":"Artificial Intelligence Initiative at Oak Ridge National Laboratory"},{"DOI":"10.13039\/100016818","name":"UT-Battelle","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}],"id":[{"id":"10.13039\/100016818","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,11,1]]},"DOI":"10.1109\/tpds.2022.3146257","type":"journal-article","created":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T22:29:34Z","timestamp":1643322574000},"page":"2885-2899","source":"Crossref","is-referenced-by-count":15,"title":["Automatic Generation of High-Performance Convolution Kernels on ARM CPUs for Deep Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6208-4102","authenticated-orcid":false,"given":"Jintao","family":"Meng","sequence":"first","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1244-3151","authenticated-orcid":false,"given":"Peng","family":"Chen","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7165-2095","authenticated-orcid":false,"given":"Mohamed","family":"Wahib","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bertil","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haidong","family":"Lan","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dou","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minwen","family":"Deng","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjie","family":"Wei","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengzhong","family":"Feng","sequence":"additional","affiliation":[{"name":"National Supercomputer Center in Shenzhen, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.11.022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3437984.3458840"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2013.01.010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2973144"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374520"},{"key":"ref58","article-title":"Learning to optimize tensor programs","author":"chen","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178496"},{"key":"ref53","first-page":"1","article-title":"likwid 5: Lightweight performance tools","author":"gruber","year":"2019","journal-title":"Proc SC19 Conf"},{"key":"ref52","article-title":"OpenBLAS library","author":"zhang","year":"0"},{"key":"ref55","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5mb model size","author":"iandola","year":"2016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EMC249363.2019.00008"},{"key":"ref54","article-title":"DenseNet: Implementing efficient convnet descriptor pyramids","author":"iandola","year":"2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2939785"},{"key":"ref17","article-title":"ARM compute library","year":"0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref19","article-title":"The NVIDIA CUDA deep neural network library (cuDNN)","year":"0"},{"key":"ref18","article-title":"The NNPACK library","author":"dukhan","year":"0"},{"key":"ref51","article-title":"Neon technology introduction","volume":"4","author":"reddy","year":"2008","journal-title":"ARM Corporation"},{"key":"ref50","article-title":"Honor of Kings &#x2014; Wikipedia, the free encyclopedia","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3229762.3229764"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441609"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"ref47","first-page":"1","article-title":"Supporting TVM on risc-V architectures","author":"lee","year":"2018","journal-title":"Proc TVM Deep Learn Compiler Conf"},{"key":"ref42","article-title":"Mnn: A universal and efficient inference engine","author":"jiang","year":"2020"},{"key":"ref41","article-title":"JAX: Autograd and XLA","year":"2021"},{"key":"ref44","article-title":"26ms inference time for resnet-50: Towards real-time execution of all DNNs on smartphone","author":"niu","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia49877.2020.9277079"},{"key":"ref49","article-title":"Openblas","author":"xianyi","year":"2012"},{"key":"ref8","article-title":"cuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333881"},{"key":"ref6","first-page":"783","article-title":"Inception-v3 for flower classification","author":"xia","year":"2017","journal-title":"Proc 2nd Int Conf Image Vis Comput"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451355"},{"key":"ref40","article-title":"TVM: End-to-end optimization stack for deep learning","author":"chen","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41321-1_2"},{"key":"ref34","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014567546"},{"key":"ref36","author":"cecka","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2837614.2837615"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2016.7936203"},{"key":"ref33","article-title":"High performance and portable convolution operators for arm-based multicore processors","author":"juan","year":"2020"},{"key":"ref32","article-title":"Ncnn","author":"ni","year":"0"},{"key":"ref2","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3446382.3448606"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.83"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64203-1_37"},{"key":"ref24","author":"baer","year":"2010","journal-title":"Microprocessor Architecture From Simple Pipelines to Chip Multiprocessors"},{"key":"ref23","article-title":"Arm dynamiq redefines multi-core computing","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2013.6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref20","article-title":"Intel oneAPI deep neural network library (oneDNN)","year":"0"},{"key":"ref22","article-title":"Arm big.little","year":"2021"},{"key":"ref21","article-title":"Cache hierarchy","year":"2019"},{"key":"ref28","article-title":"ARM NN Inference Engine","author":"tools","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476217"},{"key":"ref29","article-title":"Arm neon technologies","year":"2021"},{"key":"ref60","article-title":"Armv8-a architecture evolution","author":"brash","year":"0"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/9782123\/9695263-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9782123\/09695263.pdf?arnumber=9695263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T18:00:52Z","timestamp":1685988052000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9695263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,1]]},"references-count":60,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3146257","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":[[2022,11,1]]}}}