{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:51:10Z","timestamp":1781931070858,"version":"3.54.5"},"reference-count":30,"publisher":"Information Processing Society of Japan","issue":"0","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Information Processing"],"published-print":{"date-parts":[[2026]]},"DOI":"10.2197\/ipsjjip.34.429","type":"journal-article","created":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T22:11:11Z","timestamp":1781475071000},"page":"429-443","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid CPU-GPU Implementation of Hierarchical Matrix Generation Using a Backtracking-based Load Balancing Framework"],"prefix":"10.2197","volume":"34","author":[{"given":"Jing","family":"Xu","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Kyoto University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tasuku","family":"Hiraishi","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Science, Faculty of Engineering, Kyoto Tachibana University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyang","family":"Bai","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, RIKEN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akihiro","family":"Ida","sequence":"additional","affiliation":[{"name":"Japan Agency for Marine-Earth Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masahiro","family":"Yasugi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Networks, Kyushu Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keiichiro","family":"Fukazawa","sequence":"additional","affiliation":[{"name":"Research Institute for Humanity and Nature, National Institutes for the Humanities"},{"name":"Academic Center for Computing and Media Studies, Kyoto University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1012","reference":[{"key":"1","unstructured":"[1] Brebbia, C.A., Telles, J.C.F. and Wrobel, L.C.: <i>Boundary element techniques: Theory and applications in engineering<\/i>, Springer Science &amp; Business Media (2012)."},{"key":"2","unstructured":"[2] Stein, M.L.: <i>Interpolation of spatial data: some theory for kriging<\/i>, Springer Science &amp; Business Media (1999)."},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] Hackbusch, W. and Nowak, Z.P.: On the fast matrix multiplication in the boundary element method by panel clustering, <i>Numerische Mathematik<\/i>, Vol.54, No.4, pp.463-491 (1989).","DOI":"10.1007\/BF01396324"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] Golub, G.H. and Van Loan, C.F.: Matrix Computations, forth edition (2013).","DOI":"10.56021\/9781421407944"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] Hackbusch, W.: <i>Hierarchical Matrices: Algorithms and Analysis<\/i>, Springer (2015).","DOI":"10.1007\/978-3-662-47324-5"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] B\u00f6rm, S.: <i>Efficient numerical methods for non-local operators: H2-matrix compression, algorithms and analysis<\/i>, Vol.14, European Mathematical Society (2010).","DOI":"10.4171\/091"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] B\u00f6rm, S., Grasedyck, L. and Hackbusch, W.: Introduction to Hierarchical Matrices with Applications, <i>Engineering Analysis with Boundary Elements<\/i>, Vol.27, No.5, pp.405-422 (2003).","DOI":"10.1016\/S0955-7997(02)00152-2"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] Hackbusch, W. and B\u00f6rm, S.: Data-sparse approximation by adaptive <i>H<\/i><sup>2<\/sup>-matrices, <i>Computing<\/i>, Vol.69, No.1, pp.1-35 (2002).","DOI":"10.1007\/s00607-002-1450-4"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] Grasedyck, L. and Hackbusch, W.: Construction and arithmetics of H-matrices, <i>Computing<\/i>, Vol.70, No.4, pp.295-334 (2003).","DOI":"10.1007\/s00607-003-0019-1"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] Kriemann, R.: Parallel-matrix arithmetics on shared memory systems, <i>Computing<\/i>, Vol.74, No.3, pp.273-297 (2005).","DOI":"10.1007\/s00607-004-0102-2"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] Ida, A., Iwashita, T., Mifune, T. and Takahashi, Y.: Parallel Hierarchical Matrices with Adaptive Cross Approximation on Symmetric Multiprocessing Clusters, <i>Journal of Information Processing<\/i>, Vol.22, No.4, pp.642-650 (2014).","DOI":"10.2197\/ipsjjip.22.642"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] Iwashita, T., Ida, A., Mifune, T. and Takahashi, Y.: Software Framework for Parallel BEM Analyses with <i>H<\/i>-matrices Using MPI and OpenMP, <i>Procedia Computer Science<\/i>, Vol.108, pp.2200-2209 (online), DOI: 10.1016\/j.procs.2017.05.263 (2017).","DOI":"10.1016\/j.procs.2017.05.263"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Bai, Z., Hiraishi, T., Nakashima, H., Ida, A. and Yasugi, M.: Parallelization of matrix partitioning in construction of hierarchical matrices using task parallel languages, <i>Journal of Information Processing<\/i>, Vol.27, pp.840-851 (2019).","DOI":"10.2197\/ipsjjip.27.840"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] Bai, Z., Hiraishi, T., Ida, A. and Yasugi, M.: Parallelization of Matrix Partitioning in Hierarchical Matrix Construction on Distributed Memory Systems, <i>Journal of Information Processing<\/i>, Vol.30, pp.742-754 (online), DOI: 10.2197\/ipsjjip.30.742 (2022).","DOI":"10.2197\/ipsjjip.30.742"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] Bai, Z., Hiraishi, T., Ida, A., Yasugi, M. and Fukazawa, K.: Construction of Hierarchical Matrix on Distributed Memory Systems using a Task Parallel Language, <i>2022 10th International Symposium on Computing and Networking Workshops<\/i> (<i>CANDARW<\/i>), pp.48-54, IEEE (2022).","DOI":"10.1109\/CANDARW57323.2022.00058"},{"key":"16","unstructured":"[16] H2Opus, available from &lt;https:\/\/github.com\/ecrc\/h2opus&gt;."},{"key":"17","unstructured":"[17] STRUMPACK, available from &lt;https:\/\/github.com\/pghysels\/STRUMPACK&gt;."},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] Hiraishi, T., Yasugi, M., Umatani, S. and Yuasa, T.: Backtracking-based load balancing, <i>ACM Sigplan Notices<\/i>, Vol.44, No.4, pp.55-64 (2009).","DOI":"10.1145\/1594835.1504187"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] Xu, J., Hiraishi, T., Bai, Z., Fukazawa, K. and Yasugi, M.: Implementation of Hybrid CPU-GPU Programs in a Backtracking-based Load Balancing Framework, <i>Journal of Information Processing<\/i>, Vol.33, pp.494-506 (2025).","DOI":"10.2197\/ipsjjip.33.494"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] Bebendorf, M. and Rjasanow, S.: Adaptive low-rank approximation of collocation matrices, <i>Computing<\/i>, Vol.70, No.1, pp.1-24 (2003).","DOI":"10.1007\/s00607-002-1469-6"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] Kurz, S., Rain, O. and Rjasanow, S.: The adaptive cross-approximation technique for the 3D boundary-element method, <i>IEEE transactions on Magnetics<\/i>, Vol.38, No.2, pp.421-424 (2002).","DOI":"10.1109\/20.996112"},{"key":"22","unstructured":"[22] B\u00f6rm, S., Grasedyck, L. and Hackbusch, W.: Hierarchical Matrices. lecture note (2005)."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] Frigo, M., Leiserson, C.E. and Randall, K.H.: The implementation of the Cilk-5 multithreaded language, <i>Proc. ACM SIGPLAN 1998 Conference on Programming Language Design and Implementation<\/i>, pp.212-223 (1998).","DOI":"10.1145\/277650.277725"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] Mohr, E., Kranz, D.A. and Halstead Jr, R.H.: Lazy task creation: A technique for increasing the granularity of parallel programs, <i>Proc. 1990 ACM Conference on LISP and Functional Programming<\/i>, pp.185-197 (1990).","DOI":"10.1145\/91556.91631"},{"key":"25","unstructured":"[25] Hiraishi, T., Yasugi, M. and Yuasa, T.: A Transformation-Based Implementation of Lightweight Nested Functions, <i>IPSJ Trans. Programming<\/i>, Vol.47, No.SIG 6(PRO 29), pp.50-67 (2006)."},{"key":"26","unstructured":"[26] NVIDIA Nsight Systems, available from &lt;https:\/\/developer.nvidia.com\/nsight-systems&gt;."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] Hoshino, T., Ida, A., Hanawa, T. and Nakajima, K.: Design of Parallel BEMAnalyses Framework for SIMD Processors, <i>Computational Science - ICCS 2018<\/i> (2018).","DOI":"10.1007\/978-3-319-93698-7_46"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] Hoshino, T., Ida, A., Hanawa, T. and Nakajima, K.: Load-Balancing-Aware Parallel Algorithms of H-Matrices with Adaptive Cross Approximation for GPUs, <i>2018 IEEE International Conference on Cluster Computing<\/i> (<i>CLUSTER<\/i>), pp.35-45, IEEE (2018).","DOI":"10.1109\/CLUSTER.2018.00016"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] Augonnet, C., Thibault, S., Namyst, R. and Wacrenier, P.-A.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures, <i>European Conference on Parallel Processing<\/i>, pp.863-874, Springer (2009).","DOI":"10.1007\/978-3-642-03869-3_80"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] Bosilca, G., Bouteiller, A., Danalis, A., Faverge, M., H\u00e9rault, T. and Dongarra, J.J.: Parsec: Exploiting heterogeneity to enhance scalability, <i>Computing in Science &amp; Engineering<\/i>, Vol.15, No.6, pp.36-45 (2013).","DOI":"10.1109\/MCSE.2013.98"}],"container-title":["Journal of Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/ipsjjip\/34\/0\/34_429\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:17:12Z","timestamp":1781929032000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/ipsjjip\/34\/0\/34_429\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":30,"journal-issue":{"issue":"0","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.2197\/ipsjjip.34.429","relation":{},"ISSN":["1882-6652"],"issn-type":[{"value":"1882-6652","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}