{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:10:03Z","timestamp":1767985803657,"version":"3.49.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319699523","type":"print"},{"value":"9783319699530","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-69953-0_16","type":"book-chapter","created":{"date-parts":[[2018,3,19]],"date-time":"2018-03-19T10:54:32Z","timestamp":1521456872000},"page":"274-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Optimization of Hierarchical Matrix Computation on GPU"],"prefix":"10.1007","author":[{"given":"Satoshi","family":"Ohshima","sequence":"first","affiliation":[]},{"given":"Ichitaro","family":"Yamazaki","sequence":"additional","affiliation":[]},{"given":"Akihiro","family":"Ida","sequence":"additional","affiliation":[]},{"given":"Rio","family":"Yokota","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,3,20]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s006070050015","volume":"62","author":"W Hackbusch","year":"1999","unstructured":"Hackbusch, W.: A sparse matrix arithmetic based on H-Matrices, Part I: introduction to h-matrices. Computing 62, 89\u2013108 (1999)","journal-title":"Computing"},{"issue":"1","key":"16_CR2","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1137\/050639028","volume":"29","author":"S Chandrasekaran","year":"2006","unstructured":"Chandrasekaran, S., Dewilde, P., Gu, M., Lyons, W., Pals, T.: A fast solver for HSS representations via sparse matrices. SIAM J. Matrix Anal. Appl. 29(1), 67\u201381 (2006)","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"16_CR3","unstructured":"Ambikasaran, S.: Fast Algorithms for Dense Numerical Linear Algebra and Applications. Ph.D thesis, Stanford University (2013)"},{"issue":"8","key":"16_CR4","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1002\/cpa.21582","volume":"69","author":"KL Ho","year":"2016","unstructured":"Ho, K.L., Ying, L.: Hierarchical interpolative factorization for elliptic operators: differential equations. Commun. Pure Appl. Math. 69(8), 1415\u20131451 (2016)","journal-title":"Commun. Pure Appl. Math."},{"key":"16_CR5","unstructured":"MAGMA: MAGMA (2017). http:\/\/icl.cs.utk.edu\/magma\/ . Accessed 11 Aug 2017"},{"key":"16_CR6","unstructured":"Dongarra, J., Duff, I., Gates, M., Haidar, A., Hammarling, S., Higham, N.J., Hogg, J., Lara, P.V., Zounon, M., Relton, S.D., Tomov, S.: A Proposed API for Batched Basic Linear Algebra Subprograms. Draft Report, May 2016 (2016)"},{"key":"16_CR7","unstructured":"Batched BLAS: Batched BLAS (2017). http:\/\/icl.utk.edu\/bblas\/ . Accessed 23 Dec 2017"},{"issue":"4","key":"16_CR8","first-page":"642","volume":"22","author":"A Ida","year":"2014","unstructured":"Ida, A., Iwashita, T., Mifune, T., Takahashi, Y.: Parallel hierarchical matrices with adaptive cross approximation on symmetric multiprocessing clusters. J. Inf. Process. 22(4), 642\u2013650 (2014)","journal-title":"J. Inf. Process."},{"key":"16_CR9","doi-asserted-by":"publisher","first-page":"2200","DOI":"10.1016\/j.procs.2017.05.263","volume":"108","author":"T Iwashita","year":"2017","unstructured":"Iwashita, T., Ida, A., Mifune, T., Takahashi, Y.: Software framework for parallel BEM analyses with H-matrices using MPI and OpenMP. Procedia Comput. Sci. 108, 2200\u20132209 (2017). International Conference on Computational Science, ICCS 2017, Zurich, Switzerland, 12\u201314 June 2017","journal-title":"Procedia Comput. Sci."},{"key":"16_CR10","unstructured":"ppOpen-HPC: Open Source Infrastructure for Development and Execution of Large-Scale Scientific Applications on Post-Peta-Scale Supercomputers with Automatic Tuning (AT) (2017). http:\/\/ppopenhpc.cc.u-tokyo.ac.jp\/ppopenhpc\/ . Accessed 11 Aug 2017"},{"key":"16_CR11","unstructured":"NVIDIA: Tesla P100 Most Advanced Data Center Accelerator (2017). http:\/\/www.nvidia.com\/object\/tesla-p100.html . Accessed 11 Aug 2017"},{"key":"16_CR12","unstructured":"NVIDIA: cuBLAS: CUDA Toolkit Documentation (2017). http:\/\/docs.nvidia.com\/cuda\/cublas\/ . Accessed 11 Aug 2017"},{"key":"16_CR13","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1016\/j.procs.2017.05.237","volume":"108","author":"T Dong","year":"2017","unstructured":"Dong, T., Haidar, A., Tomov, S., Dongarra, J.: Optimizing the SVD bidiagonalization process for a batch of small matrices. Procedia Comput. Sci. 108, 1008\u20131018 (2017). International Conference on Computational Science, ICCS 2017, Zurich, Switzerland, 12\u201314 June 2017","journal-title":"Procedia Comput. Sci."},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Yamazaki, I., Abdelfattah, A., Ida, A., Ohshima, S., Tomov, S., Yokota, R., Dongarra, J.: Analyzing Performance of BiCGStab with Hierarchical Matrix on GPU cluster. In: 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (2018, in press)","DOI":"10.1109\/IPDPS.2018.00102"},{"key":"16_CR15","unstructured":"Information Technology Center, The University of Tokyo: Reedbush Supercomputer System (2017). http:\/\/www.cc.u-tokyo.ac.jp\/system\/reedbush\/index-e.html . Accessed 08 Aug 2017"},{"key":"16_CR16","unstructured":"Research Institute for Information Technology, Kyushu University: Supercomputer system ITO (2018). https:\/\/www.cc.kyushu-u.ac.jp\/scp\/system\/ITO\/ . Accessed 09 Feb 2018 (in Japanese)"},{"key":"16_CR17","unstructured":"JCAHPC (Joint Center for Advanced HPC): Oakforest-PACS (2018). http:\/\/jcahpc.jp\/eng\/ofp_intro.html . Accessed 09 Feb 2018"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Ida, A.: Lattice H-matrices on distributed-memory systems. In: 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (2018, in press)","DOI":"10.1109\/IPDPS.2018.00049"}],"container-title":["Lecture Notes in Computer Science","Supercomputing Frontiers"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-69953-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,12]],"date-time":"2019-10-12T23:55:07Z","timestamp":1570924507000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-69953-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319699523","9783319699530"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-69953-0_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}