{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T09:19:28Z","timestamp":1760347168347,"version":"3.40.3"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031695827"},{"type":"electronic","value":"9783031695834"}],"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\/978-3-031-69583-4_3","type":"book-chapter","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T19:02:05Z","timestamp":1724612525000},"page":"31-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Mixed Precision Randomized Low-Rank Approximation with\u00a0GPU Tensor Cores"],"prefix":"10.1007","author":[{"given":"Marc","family":"Baboulin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simplice","family":"Donfack","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oguz","family":"Kaya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theo","family":"Mary","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthieu","family":"Robeyns","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,26]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","unstructured":"Amestoy, P., et al.: Mixed precision low rank approximations and their application to block low rank LU factorization. IMA J. Numer. Anal. 43(4), 2198\u20132227 (2023). https:\/\/doi.org\/10.1093\/imanum\/drac037","DOI":"10.1093\/imanum\/drac037"},{"key":"3_CR2","unstructured":"Baboulin, M., Kaya, O., Mary, T., Robeyns, M.: Mixed precision iterative refinement for low-rank matrix and tensor approximations (2023). https:\/\/inria.hal.science\/hal-04115337"},{"issue":"3","key":"3_CR3","doi-asserted-by":"publisher","first-page":"C124","DOI":"10.1137\/19M1289546","volume":"42","author":"P Blanchard","year":"2020","unstructured":"Blanchard, P., Higham, N.J., Lopez, F., Mary, T., Pranesh, S.: Mixed precision block fused multiply-add: Error analysis and application to GPU tensor cores. SIAM J. Sci. Comput. 42(3), C124\u2013C141 (2020). https:\/\/doi.org\/10.1137\/19M1289546","journal-title":"SIAM J. Sci. Comput."},{"key":"3_CR4","unstructured":"Connolly, M.P., Higham, N.J., Pranesh, S.: Randomized low rank matrix approximation: rounding error analysis and a mixed precision algorithm. MIMS EPrint 2022.5, Manchester Institute for Mathematical Sciences, The University of Manchester, UK (2022). http:\/\/eprints.maths.manchester.ac.uk\/2863\/"},{"issue":"1","key":"3_CR5","doi-asserted-by":"publisher","first-page":"C1","DOI":"10.1137\/21m1465032","volume":"45","author":"M Fasi","year":"2023","unstructured":"Fasi, M., Higham, N.J., Lopez, F., Mary, T., Mikaitis, M.: Matrix multiplication in multiword arithmetic: error analysis and application to GPU tensor cores. J-SISC 45(1), C1\u2013C19 (2023). https:\/\/doi.org\/10.1137\/21m1465032","journal-title":"J-SISC"},{"issue":"2","key":"3_CR6","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1137\/090771806","volume":"53","author":"N Halko","year":"2011","unstructured":"Halko, N., Martinsson, P.G., Tropp, J.A.: Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions. SIAM Rev. 53(2), 217\u2013288 (2011). https:\/\/doi.org\/10.1137\/090771806","journal-title":"SIAM Rev."},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1017\/s0962492922000022","volume":"31","author":"NJ Higham","year":"2022","unstructured":"Higham, N.J., Mary, T.: Mixed precision algorithms in numerical linear algebra. Acta Numer. 31, 347\u2013414 (2022). https:\/\/doi.org\/10.1017\/s0962492922000022","journal-title":"Acta Numer."},{"key":"3_CR8","doi-asserted-by":"publisher","unstructured":"Lopez, F., Mary, T.: Mixed precision LU factorization on GPU tensor cores: reducing data movement and memory footprint. Int. J. High Perfor. Comput. Appl. 37(2), 165\u2013179 (2023). https:\/\/doi.org\/10.1177\/10943420221136848","DOI":"10.1177\/10943420221136848"},{"issue":"5","key":"3_CR9","doi-asserted-by":"publisher","first-page":"S485","DOI":"10.1137\/15M1026080","volume":"38","author":"PG Martinsson","year":"2016","unstructured":"Martinsson, P.G., Voronin, S.: A randomized blocked algorithm for efficiently computing rank-revealing factorizations of matrices. SIAM J. Sci. Comput. 38(5), S485\u2013S507 (2016). https:\/\/doi.org\/10.1137\/15M1026080","journal-title":"SIAM J. Sci. Comput."},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"Mary, T., Yamazaki, I., Kurzak, J., Luszczek, P., Tomov, S., Dongarra, J.: Performance of random sampling for computing low-rank approximations of a dense matrix on GPUs. In: SC 2015 - International Conference for High Performance Computing, Networking, Storage and Analysis, Austin, USA (2015). https:\/\/doi.org\/10.1145\/2807591.2807613","DOI":"10.1145\/2807591.2807613"},{"key":"3_CR11","doi-asserted-by":"publisher","unstructured":"Ootomo, H., Yokota, R.: Mixed-Precision random projection for RandNLA on tensor cores. In: Proceedings of the Platform for Advanced Scientific Computing Conference, Association for Computing Machinery, New York, Davos, Switzerland (2023). https:\/\/doi.org\/10.1145\/3592979.3593413","DOI":"10.1145\/3592979.3593413"},{"issue":"3","key":"3_CR12","doi-asserted-by":"publisher","first-page":"C307","DOI":"10.1137\/14M0973773","volume":"37","author":"I Yamazaki","year":"2015","unstructured":"Yamazaki, I., Tomov, S., Dongarra, J.: Mixed-precision cholesky QR factorization and its case studies on multicore CPU with multiple GPUs. SIAM J. Sci. Comput. 37(3), C307\u2013C330 (2015). https:\/\/doi.org\/10.1137\/14M0973773","journal-title":"SIAM J. Sci. Comput."},{"key":"3_CR13","doi-asserted-by":"publisher","unstructured":"Yamazaki, I., Tomov, S., Dongarra, J.: Sampling algorithms to update truncated SVD. In: 2017 IEEE International Conference on Big Data (Big Data), pp. 817\u2013826 (2017). https:\/\/doi.org\/10.1109\/BigData.2017.8257997","DOI":"10.1109\/BigData.2017.8257997"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2024: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-69583-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T19:02:35Z","timestamp":1724612555000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-69583-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031695827","9783031695834"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-69583-4_3","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":"26 August 2024","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":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}