{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:07:57Z","timestamp":1768403277012,"version":"3.49.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFA0700900"],"award-info":[{"award-number":["2017YFA0700900"]}],"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":["61976200"],"award-info":[{"award-number":["61976200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20181193"],"award-info":[{"award-number":["BK20181193"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2017497"],"award-info":[{"award-number":["2017497"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK2150110003"],"award-info":[{"award-number":["WK2150110003"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2020,10,1]]},"DOI":"10.1109\/tpds.2020.2990924","type":"journal-article","created":{"date-parts":[[2020,4,27]],"date-time":"2020-04-27T19:45:44Z","timestamp":1588016744000},"page":"2346-2359","source":"Crossref","is-referenced-by-count":36,"title":["A Ubiquitous Machine Learning Accelerator With Automatic Parallelization on FPGA"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9403-5575","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8391-5526","authenticated-orcid":false,"given":"Lei","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-3143","authenticated-orcid":false,"given":"Xuehai","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847340"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322226"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446050"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418008"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830789"},{"key":"ref27","first-page":"161","article-title":"Optimizing FPGA-based accelerator design for deep convolutional neural networks","author":"zhang","year":"2015","journal-title":"Proc ACM\/SIGDA Int Symp Field-Programmable Gate Arrays"},{"key":"ref29","first-page":"393","article-title":"Diannaoyu: An instruction set architecture for neural networks","author":"liu","year":"2016","journal-title":"Proc 43rd ACM\/IEEE Int Symp Comput Archit"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/527S2a"},{"key":"ref20","article-title":"An introduction to computational networks and the computational network toolkit","author":"agarwal","year":"2014"},{"key":"ref22","article-title":"DeepCL: Deep convolutional networks in OpenCL, Software","year":"2015"},{"key":"ref21","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"ref23","first-page":"1","article-title":"Optimized deep belief networks on CUDA GPUs","author":"li","year":"2015","journal-title":"Proc Int Joint Conf Neural Netw"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2013.6645501"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2012.36"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2701828"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2459316.2459320"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.17"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.13"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"884","DOI":"10.7873\/DATE.2015.0536","article-title":"SODA: Software Defined FPGA Based Accelerators for Big Data","author":"chao wang","year":"2015","journal-title":"Design Automation Test in Europe Conference Exhibition (DATE)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/1752-0509-6-94"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2015.50"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"ref13","article-title":"Caltech-256 object category dataset","author":"griffin","year":"2007"},{"key":"ref14","first-page":"1232","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","first-page":"571","article-title":"Project adam: Building an efficient and scalable deep learning training system","author":"chilimbi","year":"2014","journal-title":"Proc 11th USENIX Conf Operating Syst Des Implementation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749472"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1101\/gr.107524.110"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref19","article-title":"Theano: New features and speed improvements","author":"bastien","year":"2012","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847276"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2775054.2694358"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep leaning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref5","first-page":"161","article-title":"Optimizing FPGA-based accelerator design for deep convolutional neural networks","author":"zhang","year":"2015","journal-title":"Proc ACM\/SIGDA Int Symp Field-Programmable Gate Arrays"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847339"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1486"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2487346"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp698"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1941553.1941563"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1147\/rd.111.0025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155628"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2003.1183532"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2857078"},{"key":"ref41","first-page":"513","article-title":"DLAU: A scalable deep learning accelerator unit on FPGA","volume":"36","author":"wang","year":"2017","journal-title":"IEEE Trans Comput -Aided Des Integr Circuits Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446049"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9090388\/09079640.pdf?arnumber=9079640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:40:34Z","timestamp":1651070434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9079640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,1]]},"references-count":53,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2020.2990924","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":[[2020,10,1]]}}}