{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:32:52Z","timestamp":1743147172733,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030206550"},{"type":"electronic","value":"9783030206567"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20656-7_2","type":"book-chapter","created":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T19:02:40Z","timestamp":1559674960000},"page":"23-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Densifying Assumed-Sparse Tensors"],"prefix":"10.1007","author":[{"given":"Derya","family":"Cavdar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valeriu","family":"Codreanu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Karakus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"suffix":"III","given":"John A.","family":"Lockman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Damian","family":"Podareanu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikram","family":"Saletore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Sergeev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"suffix":"II","given":"Don D.","family":"Smith","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor","family":"Suthichai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quy","family":"Ta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srinivas","family":"Varadharajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucas A.","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rengan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,17]]},"reference":[{"key":"2_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. Computing Research Repository (CoRR), abs\/11409.0473v7, September 2014"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Gulcehre, C., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. Computing Research Repository (CoRR), abs\/1406.1078v3, September 2014","DOI":"10.3115\/v1\/D14-1179"},{"key":"2_CR3","unstructured":"Collobert, R., Puhrsch, C., Synnaeve, G.: Wav2Letter: an End-to-End ConvNet-based speech recognition system. Computing Research Repository (CoRR), abs\/1609.03193v2, September 2016"},{"key":"2_CR4","unstructured":"Gehring, J., et al.: Convolutional sequence to sequence learning. Computing Research Repository (CoRR), abs\/1705.03122v3, July 2017"},{"key":"2_CR5","unstructured":"Horovod. compute\n                      \n                        \n                      \n                      $$\\_$$\n                      \n                        \n                          _\n                        \n                      \n                    gradients() in horovod\/tensorflow\/\n                      \n                        \n                      \n                      $$\\_\\_$$\n                      \n                        \n                          \n                            _\n                            _\n                          \n                        \n                      \n                    init\n                      \n                        \n                      \n                      $$\\_\\_$$\n                      \n                        \n                          \n                            _\n                            _\n                          \n                        \n                      \n                    .py. \n                      https:\/\/github.com\/uber\/horovod\/blob\/085cb1b5f3b30734a34d047841b098c15a6e1bae\/horovod\/tensorflow\/__init__.py#L195"},{"key":"2_CR6","unstructured":"Horovod. Release 0.15.2. \n                      https:\/\/github.com\/uber\/horovod\/releases\/tag\/v0.15.2"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2_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, November 2014","DOI":"10.1145\/2647868.2654889"},{"key":"2_CR9","unstructured":"Johnson, M., et al.: Google\u2019s multilingual neural machine translation system: enabling zero-shot translation. Computing Research Repository (CoRR), abs\/1611.04558v2, August 2017"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proceedings of 2003 Human Language Technology Conference (HLT-NAACL), pp. 48\u201354, June 2003","DOI":"10.3115\/1073445.1073462"},{"key":"2_CR11","unstructured":"Kuchaiev, O., Ginsburg, B., Gitman, I., Lavrukhin, V., Case, C., Micikevicius, P.: Mixed-precision training for NLP and speech recognition with OpenSeq2Seq. Computing Research Repository (CoRR), abs\/1805.10387v2, November 2018"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Ott, M., Edunov, S., Grangier, D., Auli, M.: Scaling neural machine translation. Computing Research Repository (CoRR), abs\/1806.00187v3, September 2018","DOI":"10.18653\/v1\/W18-6301"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"2_CR14","unstructured":"Paszke, A.: Automatic differentiation in PyTorch, December 2017"},{"key":"2_CR15","unstructured":"Popel, M., Bojar, O.: Training tips for the transformer model. Computing Research Repository (CoRR), abs\/1804.00247v2, May 2018"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Rush, A.M., Chopra, S., Weston, J.: A neural attention model for abstractive sentence summarization. Computing Research Repository (CoRR), abs\/1509.00685v2, September 2015","DOI":"10.18653\/v1\/D15-1044"},{"key":"2_CR17","unstructured":"Schwan, P., et al.: Lustre: building a file system for 1000-node clusters. In: Proceedings of the 2003 Linux Symposium, vol. 2003, pp. 380\u2013386 (2003)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Stanzione, D., et al.: Stampede 2: the evolution of an XSEDE supercomputer. In: Proceedings of the Practice and Experience in Advanced Research Computing 2017 on Sustainability, Success and Impact, PEARC 2017, pp. 15:1\u201315:8. ACM, New York (2017)","DOI":"10.1145\/3093338.3093385"},{"key":"2_CR19","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS Proceedings Advances in Neural Information Processing Systems 27, pp. 3104\u20133112, December 2014"},{"key":"2_CR20","unstructured":"TensorFlow. \n                      \n                        \n                      \n                      $$\\_$$\n                      \n                        \n                          _\n                        \n                      \n                    AggregatedGrads() in tensorflow\/python\/ops\/gradients\n                      \n                        \n                      \n                      $$\\_$$\n                      \n                        \n                          _\n                        \n                      \n                    impl.py. \n                      https:\/\/github.com\/tensorflow\/tensorflow\/blob\/c95ca05536144451ef78ca6e2c15f0f65ebaaf95\/tensorflow\/python\/ops\/gradients_impl.py#L1183"},{"key":"2_CR21","unstructured":"TensorFlow. Official Transformer Model. \n                      https:\/\/github.com\/tensorflow\/models\/blob\/cdcd3ec276bdccd77a9a35c38f5aaec39c15cc0b\/official\/transformer\/README.md"},{"key":"2_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. Computing Research Repository (CoRR), abs\/1706.03762v5, December 2017"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"2_CR24","unstructured":"Yamashita, T., Hirasawa, K., Hu, J.: Application of multi-branch neural networks to stock market prediction. In: Proceedings. 2005 IEEE International Joint Conference on Neural Networks 2005, vol. 4, pp. 2544\u20132548. IEEE (2005)"},{"key":"2_CR25","unstructured":"Yamashita, T., Hirasawa, K., Hu, J., Murata, J.: Multi-branch structure of layered neural networks. In: Proceedings of the 9th International Conference on Neural Information Processing 2002, ICONIP 2002, vol. 1, pp. 243\u2013247. IEEE (2002)"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20656-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,29]],"date-time":"2020-01-29T15:00:20Z","timestamp":1580310020000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20656-7_2"}},"subtitle":["Improving Memory Efficiency and MPI Collective Performance During Tensor Accumulation for Parallelized Training of Neural Machine Translation Models"],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030206550","9783030206567"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20656-7_2","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":"17 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Frankfurt","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"16 June 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 June 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4-5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"n\/a","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}