{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:47:05Z","timestamp":1742957225577,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031408427"},{"type":"electronic","value":"9783031408434"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-40843-4_44","type":"book-chapter","created":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T12:02:32Z","timestamp":1692878552000},"page":"593-604","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GEMM-Like Convolution for\u00a0Deep Learning Inference on\u00a0the\u00a0Xilinx Versal"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9998-9503","authenticated-orcid":false,"given":"Jie","family":"Lei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5891-4479","authenticated-orcid":false,"given":"H\u00e9ctor","family":"Mart\u00ednez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9","family":"Flich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5454-165X","authenticated-orcid":false,"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,25]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Ahmad, S., et al.: Xilinx first 7 nm device: versal AI core (VC1902). In: 2019 IEEE Hot Chips 31 Symposium (HCS), pp. 1\u201328 (2019)","DOI":"10.1109\/HOTCHIPS.2019.8875639"},{"key":"44_CR2","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.jpdc.2022.05.009","volume":"167","author":"S Barrachina","year":"2022","unstructured":"Barrachina, S., et al.: Efficient and portable GEMM-based convolution operators for deep neural network training on multicore processors. J. Parallel Distrib. Comput. 167, 240\u2013254 (2022)","journal-title":"J. Parallel Distrib. Comput."},{"key":"44_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2022.102806","volume":"135","author":"S Barrachina","year":"2023","unstructured":"Barrachina, S., et al.: Reformulating the direct convolution for high-performance deep learning inference on ARM processors. J. Syst. Arch. 135, 102806 (2023)","journal-title":"J. Syst. Arch."},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Ben-Nun, T., Hoefler, T.: Demystifying parallel and distributed deep learning: an in-depth concurrency analysis. ACM Comput. Surv. 52(4), 65:1\u201365:43 (2019)","DOI":"10.1145\/3320060"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Castell\u00f3, A., Quintana-Ort\u00ed, E.S., Igual, F.D.: Anatomy of the BLIS family of algorithms for matrix multiplication. In: 30th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), pp. 92\u201399 (2022)","DOI":"10.1109\/PDP55904.2022.00023"},{"key":"44_CR6","unstructured":"Chellapilla, K., Puri, S., Simard, P.: High performance convolutional neural networks for document processing. In: International Workshop on Frontiers in Handwriting Recognition (2006). https:\/\/hal.inria.fr\/inria-00112631"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Dolz, M.F., et al.: Efficient and portable Winograd convolutions for multi-core processors. J. Supercomput. (2023, to appear)","DOI":"10.1007\/s11227-023-05088-4"},{"issue":"1","key":"44_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/77626.79170","volume":"16","author":"JJ Dongarra","year":"1990","unstructured":"Dongarra, J.J., Du Croz, J., Hammarling, S., Duff, I.: A set of level 3 basic linear algebra subprograms. ACM Trans. Math. Softw. 16(1), 1\u201317 (1990)","journal-title":"ACM Trans. Math. Softw."},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Goto, K., van de Geijn, R.A.: Anatomy of a high-performance matrix multiplication. ACM Trans. Math. Softw. 34(3), 12:1\u201312:25 (2008)","DOI":"10.1145\/1356052.1356053"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Lavin, A., Gray, S.: Fast algorithms for convolutional neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 4013\u20134021 (2016)","DOI":"10.1109\/CVPR.2016.435"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Low, T.M., et al.: Analytical modeling is enough for high-performance BLIS. ACM Trans. Math. Softw. 43(2), 12:1\u201312:18 (2016)","DOI":"10.1145\/2925987"},{"issue":"1","key":"44_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-014-0007-7","volume":"2","author":"MM Najafabadi","year":"2015","unstructured":"Najafabadi, M.M., et al.: Deep learning applications and challenges in big data analytics. J. Big Data 2(1), 1 (2015)","journal-title":"J. Big Data"},{"issue":"12","key":"44_CR13","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","volume":"105","author":"V Sze","year":"2017","unstructured":"Sze, V., et al.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295\u20132329 (2017)","journal-title":"Proc. IEEE"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Van Zee, F.G., van de Geijn, R.A.: BLIS: a framework for rapidly instantiating BLAS functionality. ACM Trans. Math. Softw. 41(3), 14:1\u201314:33 (2015)","DOI":"10.1145\/2764454"},{"key":"44_CR15","unstructured":"Xilinx: AI Engine tools and flows user guide (UG1079) (2022). https:\/\/docs.xilinx.com\/r\/en-US\/ug1079-ai-engine-kernel-coding\/Tools"},{"key":"44_CR16","unstructured":"Zhang, J., Franchetti, F., Low, T.M.: High performance zero-memory overhead direct convolutions. In: Proceedings of the 35th International Conference on Machine Learning, vol. 80 (2018)"},{"issue":"10","key":"44_CR17","doi-asserted-by":"publisher","first-page":"159","DOI":"10.3390\/a11100159","volume":"11","author":"Y Zhao","year":"2018","unstructured":"Zhao, Y., et al.: A faster algorithm for reducing the computational complexity of convolutional neural networks. Algorithms 11(10), 159 (2018)","journal-title":"Algorithms"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40843-4_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T12:08:27Z","timestamp":1692878907000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40843-4_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031408427","9783031408434"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40843-4_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"25 August 2023","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":"Hamburg","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2023","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":"49","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":"70% - 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":"2","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)"}}]}}