{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:05:10Z","timestamp":1743069910653,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030227333"},{"type":"electronic","value":"9783030227340"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-22734-0_31","type":"book-chapter","created":{"date-parts":[[2019,6,7]],"date-time":"2019-06-07T15:02:45Z","timestamp":1559919765000},"page":"427-440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scaling the Training of Recurrent Neural Networks on Sunway TaihuLight Supercomputer"],"prefix":"10.1007","author":[{"given":"Ouyi","family":"Li","sequence":"first","affiliation":[]},{"given":"Wenlai","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Xuancheng","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Yushu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Lin","family":"Gan","sequence":"additional","affiliation":[]},{"given":"Hongkun","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Jiacheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Haohuan","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Guangwen","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,8]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Arthur, P., Neubig, G., Nakamura, S.: Incorporating discrete translation lexicons into neural machine translation. arXiv preprint arXiv:1606.02006 (2016)","DOI":"10.18653\/v1\/D16-1162"},{"key":"31_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Britz, D., Goldie, A., Luong, T., Le, Q.: Massive exploration of neural machine translation architectures. arXiv preprint arXiv:1703.03906 (2017)","DOI":"10.18653\/v1\/D17-1151"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Fang, J., Fu, H., Zhao, W., Chen, B., Zheng, W., Yang, G.: swDNN: a library for accelerating deep learning applications on Sunway TaihuLight. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 615\u2013624. IEEE (2017)","DOI":"10.1109\/IPDPS.2017.20"},{"key":"31_CR5","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imageNet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"31_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-21909-7_3","volume-title":"Parallel Computing Technologies","author":"K Hasanov","year":"2015","unstructured":"Hasanov, K., Lastovetsky, A.: Hierarchical optimization of MPI reduce algorithms. In: Malyshkin, V. (ed.) PaCT 2015. LNCS, vol. 9251, pp. 21\u201334. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-21909-7_3"},{"issue":"8","key":"31_CR7","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.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675\u2013678. ACM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, L., et al.: Towards highly efficient DGEMM on the emerging SW26010 many-core processor. In: 2017 46th International Conference on Parallel Processing (ICPP), pp. 422\u2013431. IEEE (2017)","DOI":"10.1109\/ICPP.2017.51"},{"key":"31_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"31_CR11","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Scaling distributed machine learning with the parameter server. In: OSDI, vol. 14, pp. 583\u2013598 (2014)","DOI":"10.1145\/2640087.2644155"},{"issue":"6088","key":"31_CR13","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533 (1986)","journal-title":"Nature"},{"key":"31_CR14","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"31_CR15","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Scaling SGD batch size to 32K for imagenet training. arXiv preprint arXiv:1708.03888 (2017)"},{"issue":"1","key":"31_CR16","first-page":"13","volume":"15","author":"W Zhao","year":"2018","unstructured":"Zhao, W., Fu, H., Fang, J., Zheng, W., Gan, L., Yang, G.: Optimizing convolutional neural networks on the sunway taihulight supercomputer. ACM Trans. Arch. Code Optim. (TACO) 15(1), 13 (2018)","journal-title":"ACM Trans. Arch. Code Optim. (TACO)"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2019"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-22734-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T01:02:14Z","timestamp":1686099734000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-22734-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030227333","9783030227340"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-22734-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"8 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Faro","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 June 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}