{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T17:03:01Z","timestamp":1769187781421,"version":"3.49.0"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030507428","type":"print"},{"value":"9783030507435","type":"electronic"}],"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\/978-3-030-50743-5_12","type":"book-chapter","created":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T19:03:45Z","timestamp":1592247825000},"page":"230-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["DGEMM Using Tensor Cores, and Its Accurate and Reproducible Versions"],"prefix":"10.1007","author":[{"given":"Daichi","family":"Mukunoki","sequence":"first","affiliation":[]},{"given":"Katsuhisa","family":"Ozaki","sequence":"additional","affiliation":[]},{"given":"Takeshi","family":"Ogita","sequence":"additional","affiliation":[]},{"given":"Toshiyuki","family":"Imamura","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,6,15]]},"reference":[{"issue":"2","key":"12_CR1","doi-asserted-by":"publisher","first-page":"A817","DOI":"10.1137\/17M1140819","volume":"40","author":"E Carson","year":"2018","unstructured":"Carson, E., Higham, N.: Accelerating the solution of linear systems by iterative refinement in three precisions. SIAM J. Sci. Comput. 40(2), A817\u2013A847 (2018)","journal-title":"SIAM J. Sci. Comput."},{"key":"12_CR2","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1007\/BF01397083","volume":"18","author":"TJ Dekker","year":"1971","unstructured":"Dekker, T.J.: A floating-point technique for extending the available precision. Numerische Mathematik 18, 224\u2013242 (1971)","journal-title":"Numerische Mathematik"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Domke, J., et al.: Double-precision FPUs in high-performance computing: an embarrassment of riches? In: Proceedings 33rd IEEE International Parallel and Distributed Processing Symposium (IPDPS 2019), pp. 78\u201388 (2019)","DOI":"10.1109\/IPDPS.2019.00019"},{"issue":"1","key":"12_CR4","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.S.: A set of level 3 basic linear algebra subprograms. ACM Trans. Math. Softw. 16(1), 1\u201317 (1990)","journal-title":"ACM Trans. Math. Softw."},{"issue":"2","key":"12_CR5","doi-asserted-by":"publisher","first-page":"13:1","DOI":"10.1145\/1236463.1236468","volume":"33","author":"L Fousse","year":"2007","unstructured":"Fousse, L., Hanrot, G., Lef\u00e8vre, V., P\u00e9lissier, P., Zimmermann, P.: MPFR: a multiple-precision binary floating-point library with correct rounding. ACM Trans. Math. Softw. 33(2), 13:1\u201313:15 (2007)","journal-title":"ACM Trans. Math. Softw."},{"key":"12_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1007\/978-3-319-93698-7_45","volume-title":"Computational Science \u2013 ICCS 2018","author":"A Haider","year":"2018","unstructured":"Haider, A., et al.: The design of fast and energy-efficient linear solvers: on the potential of half-precision arithmetic and iterative refinement techniques. In: Shi, Y., et al. (eds.) ICCS 2018. LNCS, vol. 10860, pp. 586\u2013600. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93698-7_45"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Haidar, A., Tomov, S., Dongarra, J., Higham, N.J.: Harnessing GPU tensor cores for fast FP16 arithmetic to speed up mixed-precision iterative refinement solvers. In: Proceedings International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2018), pp. 47:1\u201347:11 (2018)","DOI":"10.1109\/SC.2018.00050"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Henry, G., Tang, P.T.P., Heinecke, A.: Leveraging the bfloat16 artificial intelligence datatype for higher-precision computations. In: Proceedings 26th IEEE Symposium on Computer Arithmetic (ARITH-26), pp. 69\u201376 (2019)","DOI":"10.1109\/ARITH.2019.00019"},{"issue":"5","key":"12_CR9","doi-asserted-by":"publisher","first-page":"A2815","DOI":"10.1137\/18M1226312","volume":"41","author":"NJ Higham","year":"2019","unstructured":"Higham, N.J., Mary, T.: A new approach to probabilistic rounding error analysis. SIAM J. Sci. Comput. 41(5), A2815\u2013A2835 (2019)","journal-title":"SIAM J. Sci. Comput."},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Ichimura, S., Katagiri, T., Ozaki, K., Ogita, T., Nagai, T.: Threaded accurate matrix-matrix multiplications with sparse matrix-vector multiplications. In: Proceedings 32nd IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). pp. 1093\u20131102 (2018)","DOI":"10.1109\/IPDPSW.2018.00168"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Markidis, S., Chien, S.W.D., Laure, E., Peng, I.B., Vetter, J.S.: NVIDIA tensor core programmability, performance precision. In: Proceedings 32nd IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 522\u2013531 (2018)","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Mukunoki, D., Ogita, T., Ozaki, K.: Reproducible BLAS routines with tunable accuracy using ozaki scheme for many-core architectures. In: Proceedings 13th International Conference on Parallel Processing and Applied Mathematics (PPAM2019), Lecture Notes in Computer Science, vol. 12043, pp. 516\u2013527 (2020)","DOI":"10.1007\/978-3-030-43229-4_44"},{"issue":"1","key":"12_CR13","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s11075-011-9478-1","volume":"59","author":"K Ozaki","year":"2012","unstructured":"Ozaki, K., Ogita, T., Oishi, S., Rump, S.M.: Error-free transformations of matrix multiplication by using fast routines of matrix multiplication and its applications. Numer. Algorithms 59(1), 95\u2013118 (2012)","journal-title":"Numer. Algorithms"},{"issue":"2","key":"12_CR14","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1137\/07068816X","volume":"31","author":"S Rump","year":"2009","unstructured":"Rump, S., Ogita, T., Oishi, S.: Accurate floating-point summation part ii: Sign, k-fold faithful and rounding to nearest. SIAM J. Sci. Comput. 31(2), 1269\u20131302 (2009)","journal-title":"SIAM J. Sci. Comput."},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Sorna, A., Cheng, X., D\u2019Azevedo, E., Won, K., Tomov, S.: Optimizing the fast fourier transform using mixed precision on tensor core hardware. In: Proceedings 25th IEEE International Conference on High Performance Computing Workshops (HiPCW), pp. 3\u20137 (2018)","DOI":"10.1109\/HiPCW.2018.8634417"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Yang, K., Chen, Y.F., Roumpos, G., Colby, C., Anderson, J.: High performance monte carlo simulation of ising model on TPU clusters. In: Proceedings International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2019), pp. 83:1\u201383:15 (2019)","DOI":"10.1145\/3295500.3356149"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-50743-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:03:57Z","timestamp":1702929837000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-50743-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030507428","9783030507435"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-50743-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"15 June 2020","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 am Main","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2020","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":"87","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":"27","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":"31% - 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":"3.73","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":"4.33","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)"}},{"value":"The conference was held virtually due to the COVID-19 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"}]}}