{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T15:05:04Z","timestamp":1781708704927,"version":"3.54.5"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319436586","type":"print"},{"value":"9783319436593","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-43659-3_35","type":"book-chapter","created":{"date-parts":[[2016,8,8]],"date-time":"2016-08-08T02:54:01Z","timestamp":1470624841000},"page":"477-489","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Redesigning Triangular Dense Matrix Computations on GPUs"],"prefix":"10.1007","author":[{"given":"Ali","family":"Charara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hatem","family":"Ltaief","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Keyes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,8,9]]},"reference":[{"key":"35_CR1","unstructured":"BLAS: Basic Linear Algebra Subprograms. \n                      http:\/\/www.netlib.org\/blas"},{"key":"35_CR2","unstructured":"Engineering and Scientific Subroutine Library (ESSL) and Parallel ESSL. \n                      http:\/\/www-03.ibm.com\/systems\/power\/software\/essl\/"},{"key":"35_CR3","unstructured":"Intel MKL Library. \n                      http:\/\/software.intel.com\/en-us\/articles\/intel-mkl"},{"key":"35_CR4","unstructured":"NVIDIA CUDA Toolkit. \n                      http:\/\/developer.nvidia.com\/cuda-toolkit"},{"key":"35_CR5","unstructured":"The NVIDIA CUDA Basic Linear Algebra Subroutines (CUBLAS). \n                      http:\/\/developer.nvidia.com\/cublas"},{"key":"35_CR6","unstructured":"CUDA C best practices guide"},{"issue":"1","key":"35_CR7","doi-asserted-by":"publisher","first-page":"012037","DOI":"10.1088\/1742-6596\/180\/1\/012037","volume":"180","author":"E Agullo","year":"2009","unstructured":"Agullo, E., Demmel, J., Dongarra, J., Hadri, B., Kurzak, J., Langou, J., Ltaief, H., Luszczek, P., Tomov, S.: Numerical linear algebra on emerging architectures: the PLASMA and MAGMA projects. J. Phys. Conf. Ser. 180(1), 012037 (2009)","journal-title":"J. Phys. Conf. Ser."},{"key":"35_CR8","unstructured":"Ahmad, A., Ltaief, H., Keyes, D.: KBLAS: an optimized library for dense matrix-vector multiplication on GPU accelerators. ACM Trans. Math. Softw. (2016) (to appear)"},{"key":"35_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/3-540-70734-4_7","volume-title":"Applied Parallel Computing. New Paradigms for HPC in Industry and Academia","author":"BS Andersen","year":"2001","unstructured":"Andersen, B.S., Gustavson, F.G., Karaivanov, A., Marinova, M., Waniewski, J., Yalamov, P.Y.: LAWRA: linear algebra with recursive algorithms. In: Gebremedhin, A.H., Manne, F., Moe, R., S\u00f8revik, T. (eds.) PARA 2000. LNCS, vol. 1947, pp. 38\u201351. Springer, Heidelberg (2001)"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Charara, A., Ltaief, H., Gratadour, D., Keyes, D.E., Sevin, A., Abdelfattah, A., Gendron, E., Morel, C., Vidal, F.: Pipelining computational stages of the tomographic reconstructor for multi-object adaptive optics on a multi-GPU system. In: Damkroger, T., Dongarra, J. (eds.) International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014, pp. 262\u2013273. IEEE (2014)","DOI":"10.1109\/SC.2014.27"},{"issue":"1","key":"35_CR11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1137\/S0036144503428693","volume":"46","author":"E Elmroth","year":"2004","unstructured":"Elmroth, E., Gustavson, F., Jonsson, I., K\u00e5gstr\u00f6m, B.: Recursive blocked algorithms and hybrid data structures for dense matrix library software. SIAM Rev. 46(1), 3\u201345 (2004)","journal-title":"SIAM Rev."},{"issue":"1","key":"35_CR12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1377603.1377607","volume":"35","author":"Kazushige Goto","year":"2008","unstructured":"Goto, K., van de Geijn, R.: High-performance implementation of the level 3 BLAS. ACM Trans. Math. Softw. 35(1), 4:1\u20134:14 (2008)","journal-title":"ACM Transactions on Mathematical Software"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Hadri, B., Fahey, M.R.: Mining software usage with the automatic library tracking database (ALTD). In: Pfeiffer, H., Ignatov, D., Poelmans, J., Gadiraju, N. (eds.) ICCS. Procedia Computer Science, vol. 18, pp. 1834\u20131843. Elsevier (2013)","DOI":"10.1016\/j.procs.2013.05.352"},{"key":"35_CR14","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718027","volume-title":"Accuracy and Stability of Numerical Algorithms","author":"NJ Higham","year":"2002","unstructured":"Higham, N.J.: Accuracy and Stability of Numerical Algorithms. SIAM, Philadelphia (2002)"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Igual, F.D., Quintana-Ort, G., van de Geijn, R.A.: Level-3 BLAS on a GPU: picking the low hanging fruit. In: AIP Conference Proceedings, vol. 1504(1), pp. 1109\u20131112 (2012)","DOI":"10.1063\/1.4772121"},{"issue":"3","key":"35_CR16","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1145\/292395.292412","volume":"24","author":"B K\u00e5gstr\u00f6m","year":"1998","unstructured":"K\u00e5gstr\u00f6m, B., Ling, P., van Loan, C.: GEMM-based level 3 BLAS: high-performance model implementations and performance evaluation benchmark. ACM Trans. Math. Softw. 24(3), 268\u2013302 (1998)","journal-title":"ACM Trans. Math. Softw."},{"issue":"4","key":"35_CR17","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1177\/1094342010385729","volume":"24","author":"R Nath","year":"2010","unstructured":"Nath, R., Tomov, S., Dongarra, J.: An improved magma GEMM for fermi graphics processing units. Int. J. High Perform. Comput. Appl. 24(4), 511\u2013515 (2010)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Nath, R., Tomov, S., Dong, T., Dongarra, J.: Optimizing symmetric dense matrix-vector multiplication on GPUs. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2011, pp. 6:1\u20136:10. ACM, New York (2011)","DOI":"10.1145\/2063384.2063392"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Volkov, V., Demmel, J.W.: Benchmarking GPUs to tune dense linear algebra. In: Proceedings of 2008 ACM\/IEEE Conference on Supercomputing, SC 2008, pp. 31:1\u201331:11. IEEE, Piscataway (2008)","DOI":"10.1109\/SC.2008.5214359"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2016: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-43659-3_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,9]],"date-time":"2020-08-09T00:06:53Z","timestamp":1596931613000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-43659-3_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319436586","9783319436593"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-43659-3_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"9 August 2016","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":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 August 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/europar2016.inria.fr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}