{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T20:05:27Z","timestamp":1783713927347,"version":"3.55.0"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031856990","type":"print"},{"value":"9783031857003","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-85700-3_2","type":"book-chapter","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T04:50:21Z","timestamp":1743569421000},"page":"17-31","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Batched DGEMMs for\u00a0Scientific Codes Running on\u00a0Long Vector Architectures"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9809-0857","authenticated-orcid":false,"given":"Fabio","family":"Banchelli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3682-9905","authenticated-orcid":false,"given":"Marta","family":"Garcia-Gasulla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3559-4825","authenticated-orcid":false,"given":"Filippo","family":"Mantovani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"2_CR1","unstructured":"Cublas batched kernels. https:\/\/docs.nvidia.com\/cuda\/cublas"},{"key":"2_CR2","unstructured":"Eigen repository. https:\/\/gitlab.com\/libeigen\/eigen"},{"key":"2_CR3","unstructured":"Introducing batch GEMM operations. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/introducing-batch-gemm-operations.html"},{"key":"2_CR4","unstructured":"Openblas repository. https:\/\/github.com\/OpenMathLib\/OpenBLAS"},{"key":"2_CR5","unstructured":"Seissol repository. https:\/\/github.com\/SeisSol\/SeisSol"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Abdelfattah, A., Haidar, A., Tomov, S., Dongarra, J.: Performance, design, and autotuning of batched gemm for gpus. In: Kunkel, J.M., Balaji, P., Dongarra, J. (eds.) High Performance Computing, pp. 21\u201338. Springer, Cham (2016)","DOI":"10.1007\/978-3-319-41321-1_2"},{"key":"2_CR7","unstructured":"Dongarra, J., et\u00a0al.: A proposed API for batched basic linear algebra subprograms (2016)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Dongarra, J., Hammarling, S., Higham, N.J., Relton, S.D., Valero-Lara, P., Zounon, M.: The design and performance of batched blas on modern high-performance computing systems. Procedia Comput. Sci. 108, 495\u2013504 (2017). international Conference on Computational Science, ICCS 2017, 12-14 June 2017, Zurich, Switzerland","DOI":"10.1016\/j.procs.2017.05.138"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Dorozhinskii, R., Bader, M.: Seissol on distributed multi-GPU systems: cuda code generation for the modal discontinuous Galerkin method. In: The International Conference on High Performance Computing in Asia-Pacific Region. HPCAsia \u201921, New York, NY, USA, pp. 69-82, Association for Computing Machinery (2021)","DOI":"10.1145\/3432261.3436753"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Heinecke, A., et al.: Petascale high order dynamic rupture earthquake simulations on heterogeneous supercomputers. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC \u201914, pp. 3\u201314. IEEE Press (2014)","DOI":"10.1109\/SC.2014.6"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Mantovani, F., et al.: Software development vehicles to enable extended and early co-design: A risc-v and hpc case of study. In: Bienz, A., Weiland, M., Baboulin, M., Kruse, C. (eds.) High Performance Computing, pp. 526\u2013537. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-40843-4_39"},{"key":"2_CR12","unstructured":"Pillet, V., Labarta, J., Cortes, T., Girona, S.: Paraver: a tool to visualize and analyze parallel code. In: Proceedings of WoTUG-18: Transputer and OCCAM Developments, vol.\u00a044, pp. 17\u201331. Citeseer (1995)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Vizcaino, P., Ieronymakis, G., Dimou, N., Papaefstathiou, V., Labarta, J., Mantovani, F.: Short reasons for long vectors in HPC CPUs: a study based on RISC-V. In: Proceedings of the SC \u201923 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, SC-W \u201923, New York, NY, USA, pp. 1543\u20131549. Association for Computing Machinery (2023)","DOI":"10.1145\/3624062.3624231"},{"issue":"3","key":"2_CR14","doi-asserted-by":"crossref","first-page":"14:1","DOI":"10.1145\/2764454","volume":"41","author":"FG Van Zee","year":"2015","unstructured":"Van Zee, F.G., van de Geijn, R.A.: BLIS: a framework for rapidly instantiating BLAS functionality. ACM Trans. Math. Software 41(3), 14:1-14:33 (2015)","journal-title":"ACM Trans. Math. Software"},{"issue":"2","key":"2_CR15","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1145\/2755561","volume":"42","author":"FG Van Zee","year":"2016","unstructured":"Van Zee, F.G., et al.: The BLIS framework: experiments in portability. ACM Trans. Math. Software 42(2), 121\u20131219 (2016)","journal-title":"ACM Trans. Math. Software"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-85700-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T04:50:35Z","timestamp":1743569435000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-85700-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031856990","9783031857003"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-85700-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PPAM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Processing and Applied Mathematics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ostrava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"9 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppam2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ppam.edu.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}