{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:40:15Z","timestamp":1742920815810,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819708079"},{"type":"electronic","value":"9789819708086"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-0808-6_16","type":"book-chapter","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T16:02:20Z","timestamp":1708963340000},"page":"277-298","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SW-LeNet: Implementation and\u00a0Optimization of\u00a0LeNet-1 Algorithm on\u00a0Sunway Bluelight II Supercomputer"],"prefix":"10.1007","author":[{"given":"Zenghui","family":"Ren","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingshan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,27]]},"reference":[{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf","key":"16_CR1"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)","key":"16_CR2"},{"issue":"11","key":"16_CR3","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.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998). https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc. IEEE"},{"unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)","key":"16_CR4"},{"doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.\u00a01\u20139 (2015)","key":"16_CR5","DOI":"10.1109\/CVPR.2015.7298594"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"16_CR6","DOI":"10.1109\/CVPR.2016.90"},{"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)","key":"16_CR7","DOI":"10.1109\/IPDPS.2017.20"},{"issue":"6","key":"16_CR8","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1016\/j.patcog.2004.01.013","volume":"37","author":"KS Oh","year":"2004","unstructured":"Oh, K.S., Jung, K.: GPU implementation of neural networks. Pattern Recogn. 37(6), 1311\u20131314 (2004)","journal-title":"Pattern Recogn."},{"key":"16_CR9","first-page":"012065","volume":"2258","author":"K Ma","year":"2022","unstructured":"Ma, K., Han, L., Shang, J., Xie, J., Zhang, H.: Optimized realization of Quantum Fourier Transform for domestic DCU accelerator. J. Phys: Conf. Ser. 2258, 012065 (2022)","journal-title":"J. Phys: Conf. Ser."},{"doi-asserted-by":"crossref","unstructured":"Zhu, Q., Luo, H., Yang, C., Ding, M., Yin, W., Yuan, X.: Enabling and scaling the HPCG benchmark on the newest generation Sunway supercomputer with 42 million heterogeneous cores. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201313 (2021)","key":"16_CR10","DOI":"10.1145\/3458817.3476158"},{"unstructured":"http:\/\/yann.lecun.com\/exdb\/mnist\/","key":"16_CR11"},{"issue":"2","key":"16_CR12","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1109\/TITS.2019.2962338","volume":"22","author":"S Kuutti","year":"2020","unstructured":"Kuutti, S., Bowden, R., Jin, Y., Barber, P., Fallah, S.: A survey of deep learning applications to autonomous vehicle control. IEEE Trans. Intell. Transp. Syst. 22(2), 712\u2013733 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"doi-asserted-by":"crossref","unstructured":"Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243 (2019)","key":"16_CR13","DOI":"10.18653\/v1\/P19-1355"},{"doi-asserted-by":"crossref","unstructured":"James, S., Wada, K., Laidlow, T., Davison, A.J.: Coarse-to-fine q-attention: efficient learning for visual robotic manipulation via discretisation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13739\u201313748 (2022)","key":"16_CR14","DOI":"10.1109\/CVPR52688.2022.01337"},{"issue":"2","key":"16_CR15","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1049\/iet-ifs.2019.0159","volume":"14","author":"N Bakhshinejad","year":"2020","unstructured":"Bakhshinejad, N., Hamzeh, A.: Parallel-CNN network for malware detection. IET Inf. Secur. 14(2), 210\u2013219 (2020)","journal-title":"IET Inf. Secur."},{"issue":"3","key":"16_CR16","doi-asserted-by":"publisher","first-page":"2679","DOI":"10.3233\/JIFS-190601","volume":"39","author":"GM Rao","year":"2020","unstructured":"Rao, G.M., Ramesh, D.: Parallel CNN based big data visualization for traffic monitoring. J. Intell. Fuzzy Syst. 39(3), 2679\u20132691 (2020)","journal-title":"J. Intell. Fuzzy Syst."},{"doi-asserted-by":"crossref","unstructured":"Kabir, H., Booth, J.D., Raghavan, P.: A multilevel compressed sparse row format for efficient sparse computations on multicore processors. In: 2014 21st International Conference on High Performance Computing (HiPC), pp. 1\u201310. IEEE (2014)","key":"16_CR17","DOI":"10.1109\/HiPC.2014.7116882"},{"issue":"1","key":"16_CR18","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1177\/1094342015597082","volume":"31","author":"S Kirmani","year":"2017","unstructured":"Kirmani, S., Park, J., Raghavan, P.: An embedded sectioning scheme for multiprocessor topology-aware mapping of irregular applications. Int. J. High Perform. Comput. Appl. 31(1), 91\u2013103 (2017)","journal-title":"Int. J. High Perform. Comput. Appl."},{"unstructured":"Chetlur, S., et al.: cuDNN: efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)","key":"16_CR19"},{"doi-asserted-by":"crossref","unstructured":"Li, L., et al.: swCaffe: a parallel framework for accelerating deep learning applications on Sunway TaihuLight. In: 2018 IEEE International Conference on Cluster Computing (CLUSTER), pp. 413\u2013422. IEEE (2018)","key":"16_CR20","DOI":"10.1109\/CLUSTER.2018.00087"},{"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 (2014)","key":"16_CR21","DOI":"10.1145\/2647868.2654889"},{"doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: 10M-core scalable fully-implicit solver for nonhydrostatic atmospheric dynamics. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2016, pp. 57\u201368. IEEE (2016)","key":"16_CR22","DOI":"10.1109\/SC.2016.5"},{"doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: 18.9-Pflops nonlinear earthquake simulation on Sunway TaihuLight: enabling depiction of 18-Hz and 8-meter scenarios. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312 (2017)","key":"16_CR23","DOI":"10.1145\/3126908.3126910"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Closing the \u201cquantum supremacy\u201d gap: achieving real-time simulation of a random quantum circuit using a New Sunway Supercomputer. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312 (2021)","key":"16_CR24","DOI":"10.1145\/3458817.3487399"},{"doi-asserted-by":"crossref","unstructured":"Shang, H., et al.: Extreme-scale ab initio Quantum Raman Spectra Simulations on the leadership HPC system in China. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201313 (2021)","key":"16_CR25","DOI":"10.1145\/3458817.3487402"},{"doi-asserted-by":"crossref","unstructured":"Ma, Z., et al.: BaGuaLu: targeting brain scale pretrained models with over 37 million cores. In: Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 192\u2013204 (2022)","key":"16_CR26","DOI":"10.1145\/3503221.3508417"},{"issue":"11","key":"16_CR27","doi-asserted-by":"publisher","first-page":"2846","DOI":"10.1109\/TPDS.2022.3145163","volume":"33","author":"M Li","year":"2022","unstructured":"Li, M., et al.: Bridging the gap between deep learning and frustrated quantum spin system for extreme-scale simulations on new generation of Sunway Supercomputer. IEEE Trans. Parallel Distrib. Syst. 33(11), 2846\u20132859 (2022)","journal-title":"IEEE Trans. Parallel Distrib. Syst."}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-0808-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T16:04:50Z","timestamp":1708963490000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0808-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819708079","9789819708086"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0808-6_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"27 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tjutanklab.com\/ica3pp2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Online submission system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"439","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":"145","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":"33% - 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":"3","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":"5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}