{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:27:05Z","timestamp":1783009625668,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tc.2020.3000118","type":"journal-article","created":{"date-parts":[[2020,6,8]],"date-time":"2020-06-08T21:36:18Z","timestamp":1591652178000},"page":"1-1","source":"Crossref","is-referenced-by-count":22,"title":["FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters"],"prefix":"10.1109","author":[{"given":"Tianqi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Herbordt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080244"},{"key":"ref38","first-page":"367","article-title":"Data-driven light field depth estimation using deep convolutional neural networks","author":"sun","year":"2016","journal-title":"Proc Int Joint Conf Neural Netw"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/FPL.2017.8056823"},{"key":"ref32","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","author":"mirhoseini","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.64"},{"key":"ref30","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","author":"lian","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00044"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2018.8547521"},{"key":"ref35","article-title":"Accelerating deep convolutional neural networks using specialized hardware","volume":"2","author":"ovtcharov","year":"2015","journal-title":"Microsoft Research Whitepaper"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00074"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062207"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2018.00021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2019.00-43"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330386"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2016.7761639"},{"key":"ref15","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"goyal","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.25"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3105925"},{"key":"ref18","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","author":"huang","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","first-page":"6660","article-title":"Training neural networks using features replay","author":"huo","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783710"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356169"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2017.73"},{"key":"ref6","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015"},{"key":"ref5","article-title":"Revisiting distributed synchronous SGD","author":"chen","year":"2016"},{"key":"ref29","article-title":"A framework for FPGA-based acceleration of neural network inference with limited numerical precision via high-level synthesis with streaming functionality","author":"lian","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MDT.2010.141"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"ref2","article-title":"Demystifying parallel and distributed deep learning: An in-depth concurrency analysis","author":"ben-nun","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"ref1","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016"},{"key":"ref20","article-title":"Decoupled parallel backpropagation with convergence guarantee","author":"huo","year":"2018"},{"key":"ref45","first-page":"107","article-title":"F-CNN: An FPGA-based framework for training convolutional neural networks","author":"zhao","year":"2016","journal-title":"Proc IEEE 27th Int Conf Appl -specific Syst Architectures Processors"},{"key":"ref22","article-title":"Exploring hidden dimensions in parallelizing convolutional neural networks","author":"jia","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356179"},{"key":"ref24","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref41","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref23","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56258-2_22"},{"key":"ref26","article-title":"TensorFlow VGG-16 benchmark","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934644"},{"key":"ref25","article-title":"TensorFlow AlexNet benchmark","year":"2018"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/4358213\/09110747.pdf?arnumber=9110747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:09:57Z","timestamp":1651068597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9110747\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tc.2020.3000118","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":[[2020]]}}}