{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:08:07Z","timestamp":1766268487190,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030576745"},{"type":"electronic","value":"9783030576752"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-57675-2_16","type":"book-chapter","created":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T23:12:33Z","timestamp":1597705953000},"page":"248-262","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Optimizing FFT-Based Convolution on ARMv8 Multi-core CPUs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8286-6566","authenticated-orcid":false,"given":"Qinglin","family":"Wang","sequence":"first","affiliation":[]},{"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiandong","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Siqi","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Songzhu","family":"Mei","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,8,18]]},"reference":[{"issue":"23","key":"16_CR1","doi-asserted-by":"publisher","first-page":"e4800","DOI":"10.1002\/cpe.4800","volume":"30","author":"X Chen","year":"2018","unstructured":"Chen, X., Xie, P., Chi, L., Liu, J., Gong, C.: An efficient simd compression format for sparse matrix-vector multiplication. Concurr. Comput.: Pract. Experience 30(23), e4800 (2018)","journal-title":"Concurr. Comput.: Pract. Experience"},{"issue":"90","key":"16_CR2","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1090\/S0025-5718-1965-0178586-1","volume":"19","author":"JW Cooley","year":"1965","unstructured":"Cooley, J.W., Tukey, J.W.: An algorithm for the machine calculation of complex fourier series. Math. Comput. 19(90), 297\u2013301 (1965)","journal-title":"Math. Comput."},{"key":"16_CR3","unstructured":"Dukhan, M.: NNPACK (2019). https:\/\/github.com\/Maratyszcza\/NNPACK. Accessed 3 Jan 2019"},{"key":"16_CR4","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)"},{"issue":"3","key":"16_CR5","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1145\/1356052.1356053","volume":"34","author":"K Goto","year":"2008","unstructured":"Goto, K., Geijn, R.A.V.D.: Anatomy of high-performance matrix multiplication. ACM Trans. Math. Softw. (TOMS) 34(3), 12 (2008)","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"16_CR7","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":"16_CR8","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Lavin, A., Gray, S.: Fast algorithms for convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4013\u20134021 (2016)","DOI":"10.1109\/CVPR.2016.435"},{"key":"16_CR10","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2016.11.046","volume":"230","author":"S Li","year":"2017","unstructured":"Li, S., Dou, Y., Niu, X., Lv, Q., Wang, Q.: A fast and memory saved gpu acceleration algorithm of convolutional neural networks for target detection. Neurocomputing 230, 48\u201359 (2017)","journal-title":"Neurocomputing"},{"key":"16_CR11","unstructured":"Mathieu, M., Henaff, M., Lecun, Y.: Fast training of convolutional networks through FFTS. In: International Conference on Learning Representations (ICLR2014), CBLS, April 2014 (2014)"},{"key":"16_CR12","unstructured":"Phytium: FT-1500A\/16 (2020). http:\/\/www.phytium.com.cn\/Product\/detail?language=1&product_id=9. Accessed 3 Jan 2020"},{"key":"16_CR13","unstructured":"Phytium: FT-2000plus\/64 (2020). http:\/\/www.phytium.com.cn\/Product\/detail?language=1&product_id=7. Accessed 3 Jan 2020"},{"key":"16_CR14","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"16_CR15","unstructured":"Vasilache, N., Johnson, J., Mathieu, M., Chintala, S., Piantino, S., LeCun, Y.: Fast convolutional nets with FBFFT: a GPU performance evaluation. In: 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings, San Diego, CA, USA, 7\u20139 May 2015 (2015)"},{"issue":"6","key":"16_CR16","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.7544\/issn1000-1239.2020.20200107","volume":"57","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Li, D., Mei, S., Lai, Z., Dou, Y.: Optimizing winograd-based fast convolution algorithm on phytium multi-core CPUs (in Chinese). J. Comput. Res. Dev. 57(6), 1140\u20131151 (2020). https:\/\/doi.org\/10.7544\/issn1000-1239.2020.20200107","journal-title":"J. Comput. Res. Dev."},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"Wang, Q., Songzhu, M., Liu, J., Gong, C.: Parallel convolution algorithm using implicit matrix multiplication on multi-core CPUs. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137, July 2019. https:\/\/doi.org\/10.1109\/IJCNN.2019.8852012","DOI":"10.1109\/IJCNN.2019.8852012"},{"key":"16_CR18","unstructured":"Zhang, J., Franchetti, F., Low, T.M.: High performance zero-memory overhead direct convolutions. In: International Conference on Machine Learning, pp. 5771\u20135780 (2018)"},{"key":"16_CR19","unstructured":"Zlateski, A., Jia, Z., Li, K., Durand, F.: FFT convolutions are faster than winograd on modern CPUs, here is why. arXiv preprint arXiv:1809.07851 (2018)"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Zlateski, A., Lee, K., Seung, H.S.: ZNN-a fast and scalable algorithm for training 3D convolutional networks on multi-core and many-core shared memory machines. In: 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 801\u2013811. IEEE (2016)","DOI":"10.1109\/IPDPS.2016.119"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Zlateski, A., Lee, K., Seung, H.S.: ZNN i: maximizing the inference throughput of 3d convolutional networks on CPUs and GPUs. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, p. 73. IEEE Press (2016)","DOI":"10.1109\/SC.2016.72"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2020: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-57675-2_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T00:03:37Z","timestamp":1723939417000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-57675-2_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030576745","9783030576752"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-57675-2_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"18 August 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Warsaw","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2020.euro-par.org\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"158","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":"39","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":"25% - 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","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":"2.5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the coronavirus pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}