{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T06:10:50Z","timestamp":1781763050610,"version":"3.54.5"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2020,7,19]],"date-time":"2020-07-19T00:00:00Z","timestamp":1595116800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,7,19]],"date-time":"2020-07-19T00:00:00Z","timestamp":1595116800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1007\/s10115-020-01487-8","type":"journal-article","created":{"date-parts":[[2020,7,19]],"date-time":"2020-07-19T17:02:33Z","timestamp":1595178153000},"page":"4169-4197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Fast LSTM by dynamic decomposition on cloud and distributed systems"],"prefix":"10.1007","volume":"62","author":[{"given":"Yang","family":"You","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samyam","family":"Rajbhandari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cho-Jui","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kurt","family":"Keutzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Demmel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,7,19]]},"reference":[{"key":"1487_CR1","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M et al (2016) Tensorflow: a system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI), vol 16. pp 265\u2013283"},{"key":"1487_CR2","unstructured":"Amodei D, Ananthanarayanan S, Anubhai R, Bai J, Battenberg E, Case C, Casper J, Catanzaro B, Cheng Q, Chen G, et al (2016) Deep speech 2: end-to-end speech recognition in english and mandarin. In: International conference on machine learning, pp 173\u2013182"},{"issue":"2","key":"1487_CR3","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157\u2013166","journal-title":"IEEE Trans Neural Netw"},{"key":"1487_CR4","doi-asserted-by":"crossref","unstructured":"Benkrid K, Belkacemi S (2002) Design and implementation of a 2d convolution core for video applications on fpgas. In: Third international workshop on digital and computational video, 2002. DCV 2002. proceedings. IEEE, pp 85\u201392","DOI":"10.1109\/DCV.2002.1218747"},{"key":"1487_CR5","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-642-35289-8_25","volume-title":"Neural networks: tricks of the trade","author":"L Bottou","year":"2012","unstructured":"Bottou L (2012) Stochastic gradient descent tricks. In: Montavon G, Orr G, M\u00fcller K-R (eds) Neural networks: tricks of the trade. Springer, New York, pp 421\u2013436"},{"key":"1487_CR6","doi-asserted-by":"crossref","unstructured":"Cardells-Tormo F, Molinet P-L (2005) Area-efficient 2-d shift-variant convolvers for fpga-based digital image processing. In: IEEE workshop on signal processing systems design and implementation. IEEE, pp 209\u2013213","DOI":"10.1109\/TCSII.2005.857091"},{"key":"1487_CR7","unstructured":"Chelba C, Mikolov T, Schuster M, Ge Q, Brants T, Koehn P, Robinson T (2013) One billion word benchmark for measuring progress in statistical language modeling. arXiv:1312.3005"},{"key":"1487_CR8","doi-asserted-by":"crossref","unstructured":"Cloutier J, Cosatto E, Pigeon S, Boyer FR, Simard PY (1996) Vip: An fpga-based processor for image processing and neural networks. In: Proceedings of fifth international conference on microelectronics for neural networks. IEEE, pp 330\u2013336","DOI":"10.1109\/MNNFS.1996.493811"},{"key":"1487_CR9","unstructured":"Dean J, Corrado G, Monga R, Chen K, Devin M, Mao M, Ranzato M, Senior A, Tucker P, Yang K, et al (2012) Large scale distributed deep networks. In: Advances in neural information processing systems, pp 1223\u20131231"},{"issue":"6","key":"1487_CR10","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"S Deerwester","year":"1990","unstructured":"Deerwester S, Dumais ST, Furnas GW, Landauer TK, Harshman R (1990) Indexing by latent semantic analysis. J Am Soc Inf Sci 41(6):391","journal-title":"J Am Soc Inf Sci"},{"key":"1487_CR11","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971446","volume-title":"Applied numerical linear algebra","author":"JW Demmel","year":"1997","unstructured":"Demmel JW (1997) Applied numerical linear algebra, vol 56. Siam, USA"},{"key":"1487_CR12","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1487_CR13","unstructured":"Denton EL, Zaremba W, Bruna J, LeCun Y, Fergus R (2014) Exploiting linear structure within convolutional networks for efficient evaluation. In: Advances in neural information processing systems, pp 1269\u20131277"},{"key":"1487_CR14","unstructured":"Eldan R, Shamir O (2016) The power of depth for feedforward neural networks. In: Conference on learning theory, pp 907\u2013940"},{"issue":"2","key":"1487_CR15","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/s11265-005-4961-3","volume":"40","author":"RG Giron\u00e9s","year":"2005","unstructured":"Giron\u00e9s RG, Palero RC, Boluda JC, Cort\u00e9s AS (2005) Fpga implementation of a pipelined on-line backpropagation. J VLSI Signal Process Syst Signal Image Video Technol 40(2):189\u2013213","journal-title":"J VLSI Signal Process Syst Signal Image Video Technol"},{"key":"1487_CR16","unstructured":"Grave E, Joulin A, Ciss\u00e9 M, Grangier D, J\u00e9gou H (2016) Efficient softmax approximation for gpus. arXiv:1609.04309"},{"key":"1487_CR17","doi-asserted-by":"crossref","unstructured":"Han S, Liu X, Mao H, Pu J, Pedram A, Horowitz MA, Dally WJ (2016) Eie: efficient inference engine on compressed deep neural network. In: 2016 ACM\/IEEE 43rd annual international symposium on, computer architecture (ISCA). IEEE, pp 243\u2013254","DOI":"10.1109\/ISCA.2016.30"},{"key":"1487_CR18","unstructured":"Han S, Mao H, Dally WJ (2015) Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv:1510.00149"},{"key":"1487_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"1487_CR20","unstructured":"He Z, Gao S, Xiao L, Liu D, He H, Barber D (2017) Wider and deeper, cheaper and faster: tensorized lstms for sequence learning. In: Advances in neural information processing systems, pp 1\u201311"},{"issue":"8","key":"1487_CR21","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"1487_CR22","unstructured":"Hu R, Andreas J, Rohrbach M, Darrell T, Saenko K Learning to reason: end-to-end module networks for visual question answering"},{"key":"1487_CR23","doi-asserted-by":"crossref","unstructured":"Hu R, Rohrbach M, Andreas J, Darrell T, Saenko K (2017) Modeling relationships in referential expressions with compositional modular networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 4418\u20134427","DOI":"10.1109\/CVPR.2017.470"},{"key":"1487_CR24","unstructured":"Huang Y, Cheng Y, Bapna A, Firat O, Chen D, Chen M, Lee H, Ngiam J, Le QV, Wu Y, et al (2019) Gpipe: Efficient training of giant neural networks using pipeline parallelism. In: Advances in neural information processing systems, pp 103\u2013112"},{"key":"1487_CR25","doi-asserted-by":"crossref","unstructured":"Jouppi NP, Young C, Patil N, Patterson D, Agrawal G, Bajwa R, Bates S, Bhatia S, Boden N, Borchers A, et al (2017) In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th annual international symposium on computer architecture, pp 1\u201312","DOI":"10.1145\/3079856.3080246"},{"key":"1487_CR26","unstructured":"Jozefowicz R, Vinyals O, Schuster M, Shazeer N, Wu Y (2016) Exploring the limits of language modeling. arXiv:1602.02410"},{"key":"1487_CR27","unstructured":"Keskar NS, Mudigere D, Nocedal J, Smelyanskiy M, Tang PTP (2016) On large-batch training for deep learning: Generalization gap and sharp minima. arXiv:1609.04836"},{"key":"1487_CR28","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980"},{"key":"1487_CR29","unstructured":"Kuchaiev O, Ginsburg B (2017) Factorization tricks for lstm networks. arXiv:1703.10722"},{"issue":"11","key":"1487_CR30","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"1487_CR31","unstructured":"Lei T, Zhang Y (2017) Training rnns as fast as cnns. arXiv:1709.02755"},{"key":"1487_CR32","unstructured":"Lin Y, Han S, Mao H, Wang Y, Dally WJ (2017) Deep gradient compression: Reducing the communication bandwidth for distributed training. arXiv:1712.01887"},{"key":"1487_CR33","unstructured":"Luong M, Brevdo E, Zhao R (2017) Neural machine translation (seq2seq) tutorial. https:\/\/github.com\/tensorflow\/nmt"},{"key":"1487_CR34","unstructured":"Maas AL, Daly RE, Pham PT, Huang D, Ng AY, Potts C (2011) Learning word vectors for sentiment analysis. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, Portland, Oregon, USA association for computational linguistics, pp 142\u2013150"},{"issue":"2","key":"1487_CR35","first-page":"313","volume":"19","author":"MP Marcus","year":"1993","unstructured":"Marcus MP, Marcinkiewicz MA, Santorini B (1993) Building a large annotated corpus of english: The penn treebank. Computational linguistics 19(2):313\u2013330","journal-title":"Computational linguistics"},{"key":"1487_CR36","unstructured":"Narang S, Undersander E, Diamos G (2017) Block-sparse recurrent neural networks. arXiv:1711.02782"},{"key":"1487_CR37","unstructured":"Nichols KR, Moussa MA, Areibi SM (2002) Feasibility of floating-point arithmetic in fpga based artificial neural networks. In: In CAINE. Citeseer"},{"key":"1487_CR38","unstructured":"Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: International conference on machine learning, pp 1310\u20131318"},{"key":"1487_CR39","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in pytorch"},{"key":"1487_CR40","unstructured":"Sainath TN, Kingsbury B, Sindhwani V, Arisoy E, Ramabhadran B Low-rank matrix factorization for deep neural network training with high-dimensional output targets"},{"key":"1487_CR41","doi-asserted-by":"crossref","unstructured":"Sak H, Senior A, Beaufays F (2014) Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: Fifteenth annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2014-80"},{"issue":"1","key":"1487_CR42","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1109\/TNN.2006.883002","volume":"18","author":"AW Savich","year":"2007","unstructured":"Savich AW, Moussa M, Areibi S (2007) The impact of arithmetic representation on implementing mlp-bp on fpgas: A study. IEEE Trans Neural Netw 18(1):240\u2013252","journal-title":"IEEE Trans Neural Netw"},{"issue":"2","key":"1487_CR43","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1007\/s10064-019-01591-2","volume":"79","author":"MO Schwartz","year":"2020","unstructured":"Schwartz MO (2020) Groundwater contamination associated with a potential nuclear waste repository at yucca mountain. USA Bull Eng Geol Environ 79(2):1125\u20131136","journal-title":"USA Bull Eng Geol Environ"},{"key":"1487_CR44","doi-asserted-by":"publisher","first-page":"7823","DOI":"10.1109\/ACCESS.2018.2890150","volume":"7","author":"A Shawahna","year":"2018","unstructured":"Shawahna A, Sait SM, El-Maleh A (2018) Fpga-based accelerators of deep learning networks for learning and classification: A review. IEEE Access 7:7823\u20137859","journal-title":"IEEE Access"},{"key":"1487_CR45","unstructured":"Shazeer N, Cheng Y, Parmar N, Tran D, Vaswani A, Koanantakool P, Hawkins P, Lee H, Hong M, Young C, et al (2018) Mesh-tensorflow: Deep learning for supercomputers. In: Advances in neural information processing systems, pp 10414\u201310423"},{"key":"1487_CR46","unstructured":"Shim K, Lee M, Choi I, Boo Y, Sung W (2017) Svd-softmax: Fast softmax approximation on large vocabulary neural networks. In: Advances in neural information processing systems, pp 5469\u20135479"},{"key":"1487_CR47","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"issue":"1","key":"1487_CR48","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1109\/72.737503","volume":"10","author":"SC Sivakumar","year":"1999","unstructured":"Sivakumar SC, Robertson W, Phillips WJ (1999) Online stabilization of block-diagonal recurrent neural networks. IEEE Trans Neural Netw 10(1):167\u2013175","journal-title":"IEEE Trans Neural Netw"},{"issue":"1","key":"1487_CR49","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1177\/1094342005051521","volume":"19","author":"R Thakur","year":"2005","unstructured":"Thakur R, Rabenseifner R, Gropp W (2005) Optimization of collective communication operations in mpich. The Intern J High Perform Comput Appl 19(1):49\u201366","journal-title":"The Intern J High Perform Comput Appl"},{"key":"1487_CR50","doi-asserted-by":"crossref","unstructured":"Tjandra A, Sakti S, Nakamura S (2017) Compressing recurrent neural network with tensor train. In: 2017 international joint conference on, Neural networks (IJCNN). IEEE, pp 4451\u20134458","DOI":"10.1109\/IJCNN.2017.7966420"},{"key":"1487_CR51","doi-asserted-by":"crossref","unstructured":"Tjandra A, Sakti S, Nakamura S (2018) Tensor decomposition for compressing recurrent neural network. In: 2018 international joint conference on neural networks (IJCNN), IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN.2018.8489213"},{"issue":"3","key":"1487_CR52","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF02289464","volume":"31","author":"LR Tucker","year":"1966","unstructured":"Tucker LR (1966) Some mathematical notes on three-mode factor analysis. Psychometrika 31(3):279\u2013311","journal-title":"Psychometrika"},{"key":"1487_CR53","unstructured":"Wen W, He Y, Rajbhandari S, Wang W, Liu F, Hu B, Chen Y, Li H (2017) Learning intrinsic sparse structures within long short-term memory. arXiv:1709.05027"},{"key":"1487_CR54","unstructured":"Wolf DF, Romero RA, Marques E (2001) Using embedded processors in hardware models of artificial neural networks. In: Simp\u00f3sio Brasileiro de Automa\u00e7\u00e3o Inteligente, vol 9. Brasil"},{"key":"1487_CR55","doi-asserted-by":"crossref","unstructured":"Wu C-Y, Ahmed A, Beutel A, Smola AJ, Jing H (2017) Recurrent recommender networks. In: Proceedings of the tenth ACM international conference on web search and data mining. ACM, pp 495\u2013503","DOI":"10.1145\/3018661.3018689"},{"key":"1487_CR56","unstructured":"Wu Y, Schuster M, Chen Z, Le QV, Norouzi M, Macherey W, Krikun M, Cao Y, Gao Q, Macherey K, et al (2016) Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv:1609.08144"},{"key":"1487_CR57","doi-asserted-by":"crossref","unstructured":"Xiong W, Droppo J, Huang X, Seide F, Seltzer M, Stolcke A, Yu D, Zweig G (2016) Achieving human parity in conversational speech recognition. arXiv:1610.05256","DOI":"10.1109\/TASLP.2017.2756440"},{"key":"1487_CR58","unstructured":"Xu C, Yao J, Lin Z, Ou W, Cao Y, Wang Z, Zha H (2018) Alternating multi-bit quantization for recurrent neural networks. arXiv:1802.00150"},{"key":"1487_CR59","doi-asserted-by":"crossref","unstructured":"You Y, Bulu\u00e7 A, Demmel J (2017) Scaling deep learning on gpu and knights landing clusters. In: Proceedings of the international conference for high performance computing, networking, storage and analysis. ACM, p 9","DOI":"10.1145\/3126908.3126912"},{"key":"1487_CR60","unstructured":"You Y, Li J, Reddi S, Hseu J, Kumar S, Bhojanapalli S, Song X, Demmel J, Hsieh C-J (2019) Large batch optimization for deep learning: training bert in 76 minutes. arXiv:1904.00962"},{"key":"1487_CR61","doi-asserted-by":"crossref","unstructured":"You Y, Zhang Z, Hsieh C-J, Demmel J, Keutzer K (2018) Imagenet training in minutes. In: Proceedings of the 47th international conference on parallel processing. ACM, p 1","DOI":"10.1145\/3225058.3225069"},{"key":"1487_CR62","doi-asserted-by":"crossref","unstructured":"Zhai S, Chang K-h, Zhang R, Zhang ZM (2016) Deepintent: Learning attentions for online advertising with recurrent neural networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 1295\u20131304","DOI":"10.1145\/2939672.2939759"},{"issue":"11","key":"1487_CR63","doi-asserted-by":"publisher","first-page":"2072","DOI":"10.1109\/TCAD.2017.2785257","volume":"38","author":"C Zhang","year":"2018","unstructured":"Zhang C, Sun G, Fang Z, Zhou P, Pan P, Cong J (2018) Caffeine: Toward uniformed representation and acceleration for deep convolutional neural networks. IEEE Trans Comput-aided Des Integr Circuits and Syst 38(11):2072\u20132085","journal-title":"IEEE Trans Comput-aided Des Integr Circuits and Syst"},{"issue":"2","key":"1487_CR64","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1109\/TCSII.2006.886898","volume":"54","author":"H Zhang","year":"2007","unstructured":"Zhang H, Xia M, Hu G (2007) A multiwindow partial buffering scheme for fpga-based 2-d convolvers. IEEE Trans Circuits Syst II: Express Br 54(2):200\u2013204","journal-title":"IEEE Trans Circuits Syst II: Express Br"},{"key":"1487_CR65","unstructured":"Zhu M, Rhu M, Clemons J, Keckler SW, Xie Y (2016) Training long short-term memory with sparsified stochastic gradient descent"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-020-01487-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-020-01487-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-020-01487-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T07:45:50Z","timestamp":1667461550000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-020-01487-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,19]]},"references-count":65,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["1487"],"URL":"https:\/\/doi.org\/10.1007\/s10115-020-01487-8","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,19]]},"assertion":[{"value":"20 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}