{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T08:43:38Z","timestamp":1780994618354,"version":"3.54.1"},"reference-count":33,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2018,9,1]]},"DOI":"10.1587\/transinf.2017edp7176","type":"journal-article","created":{"date-parts":[[2018,8,31]],"date-time":"2018-08-31T22:42:17Z","timestamp":1535755337000},"page":"2307-2314","source":"Crossref","is-referenced-by-count":10,"title":["A Machine Learning-Based Approach for Selecting SpMV Kernels and Matrix Storage Formats"],"prefix":"10.1587","volume":"E101.D","author":[{"given":"Hang","family":"CUI","sequence":"first","affiliation":[{"name":"Graduate School of Information Sciences, Tohoku University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoichi","family":"HIRASAWA","sequence":"additional","affiliation":[{"name":"Information Systems Architecture Science Research Division, National Institute of Informatics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroaki","family":"KOBAYASHI","sequence":"additional","affiliation":[{"name":"Graduate School of Information Sciences, Tohoku University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroyuki","family":"TAKIZAWA","sequence":"additional","affiliation":[{"name":"Graduate School of Information Sciences, Tohoku University"},{"name":"Cyberscience Center, Tohoku University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] http:\/\/image-net.org\/, 2014."},{"key":"2","unstructured":"[2] http:\/\/opencv.org\/, 2016."},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] W. Abu-Sufah and A.A. Karim, \u201cAuto-tuning of sparse matrix-vector multiplication on graphics processors,\u201d Supercomputing, Lecture Notes in Computer Science, vol.7905, pp.151-164, Springer Berlin Heidelberg, Berlin, Heidelberg, 2013. 10.1007\/978-3-642-38750-0_12","DOI":"10.1007\/978-3-642-38750-0_12"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] N. Bell and M. Garland, \u201cImplementing sparse matrix-vector multiplication on throughput-oriented processors,\u201d Proc. Conference on High Performance Computing Networking, Storage and Analysis, Article No. 18, Nov. 2009. 10.1145\/1654059.1654078","DOI":"10.1145\/1654059.1654078"},{"key":"5","unstructured":"[5] S. Bhowmick, V. Eijkhout, Y. Freund, E. Fuentes, and D. Keyes, \u201cApplication of machine learning in selecting sparse linear solvers,\u201d International Journal of High Performance Computing Applications, 2006 (submitted)."},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] R. Collobert and J. Weston, \u201cA unified architecture for natural language processing: Deep neural network with multitask learning,\u201d Proc. 25th International Conference on Machine Learning, pp.160-167, 2008. 10.1145\/1390156.1390177","DOI":"10.1145\/1390156.1390177"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] H. Cui, S. Hirasawa, H. Takizawa, and H. Kobayashi, \u201cA code selection mechanism using deep learning,\u201d 2016 IEEE 10th International Symposium on Embedded Multicore\/Many-core Systems-on-Chip (MCSoC), pp.385-392, 2016. 10.1109\/mcsoc.2016.46","DOI":"10.1109\/MCSoC.2016.46"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] T.A. Davis and Y. Hu, \u201cThe university of Florida sparse matrix collection,\u201d ACM Trans. Mathematical Software, vol.38, no.1, Article No. 1, Nov. 2011. 10.1145\/2049662.2049663","DOI":"10.1145\/2049662.2049663"},{"key":"9","unstructured":"[9] X. Glorot, A. Bordes, and Y. Bengio, \u201cDomain adaptation for large-scale sentiment classification: A deep learning approach,\u201d Proc. 28th International Conference on Machine Learning, pp.513-520, 2011."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] D. Grewe and A. Lokhmotov, \u201cAutomatically generating and tuning GPU code for sparse matrix-vector multiplication from a high-level representation,\u201d Proc. Fourth Workshop on General Purpose Processing on Graphics Processing Units, GPGPU-4, Article No. 12, 2011. 10.1145\/1964179.1964196","DOI":"10.1145\/1964179.1964196"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] T. Hoefler and R. Belli, \u201cScientific benchmarking of parallel computing systems: Twelve ways to tell the masses when reporting performance results,\u201d Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC'15), Article No. 73, 2015. 10.1145\/2807591.2807644","DOI":"10.1145\/2807591.2807644"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] K. Kourtis, V. Karakasis, G. Goumas, and N. Koziris, \u201cCSX: An extended compression format for SpMV on shared memory systems,\u201d Proc. 16th ACM Symposium on Principles and Practice of Parallel Programming, pp.247-256, 2011. 10.1145\/1941553.1941587","DOI":"10.1145\/1941553.1941587"},{"key":"13","unstructured":"[13] A. Krizhevsky, I. Sutskever, and G.E. Hinton, \u201cImageNet classification with deep convolutional neural networks,\u201d Neural Information Processing Systems, pp.1097-1105, Dec. 2012."},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] D. Langr and P. Tvrd\u00edk, \u201cEvaluation criteria for sparse matrix storage formats,\u201d IEEE Trans. Parallel Distrib. Syst., vol.27, no.2, pp.428-440, 2016. 10.1109\/tpds.2015.2401575","DOI":"10.1109\/TPDS.2015.2401575"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] Y. LeCun, Y. Bengio, and G. Hinton, \u201cDeep learning,\u201d Nature, vol.521, no.7553, pp.436-444, 2015. 10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, \u201cGradient-based learning applied to document recognition,\u201d Proc. IEEE, vol.86, pp.2278-2324, Nov. 1998. 10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] S. Lee and R. Eigenmann, \u201cAdaptive runtime tuning of parallel sparse matrix-vector multiplication on distributed memory systems,\u201d Proc. 22nd Annual International Conference on Supercomputing, pp.195-204, 2008. 10.1145\/1375527.1375558","DOI":"10.1145\/1375527.1375558"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] J. Li, G. Tian, M. Chen, and N. Sun, \u201cSMAT: An input adaptive auto-tuner for sparse matrix-vector multiplication,\u201d Proc. 34th ACM SIGPLAN Conference on Programming Language Design and Implementation, pp.117-126, June 2013. 10.1145\/2491956.2462181","DOI":"10.1145\/2491956.2462181"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] S. Muralidharan, M. Shantharam, M. Hall, M. Garland, and B. Catanzaro, \u201cNitro: A framework for adaptive code variant tuning,\u201d 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp.19-23, May 2014. 10.1109\/ipdps.2014.59","DOI":"10.1109\/IPDPS.2014.59"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] M. Ozeki and T. Okatani, \u201cUnderstanding convolutional neural networks in terms of category-level attributes,\u201d Computer Vision-ACCV 2014, Lecture Notes in Computer Science, vol.9004, pp.362-375, Springer International Publishing, Cham, 2015. 10.1007\/978-3-319-16808-1_25","DOI":"10.1007\/978-3-319-16808-1_25"},{"key":"21","unstructured":"[21] L. Page, S. Brin, R. Motwani, and T. Winograd, \u201cThe pagerank citation ranking: Bringing order to the web,\u201d Technical Report, Stanford InfoLab, Nov. 1999."},{"key":"22","unstructured":"[22] N. Reddy, R. Prakash, and R.M. Reddy, \u201cNew sparse matrix storage format to improve the performance of total SpMV time,\u201d Scalable Computing: Practice and Experience, vol.13, no.2, pp.159-171, 2012."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] K. Sakurada and T. Okatani, \u201cChange detection from a street image pair using CNN features and superpixel segmentation,\u201d BMVC 2015, pp.61.1-61.12, Sept. 2015. 10.5244\/c.29.61","DOI":"10.5244\/C.29.61"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] Y. Shan, T. Wu, Y. Wang, B. Wang, Z. Wang, N. Xu, and H. Yang, \u201cFPGA and GPU implementation of large scale SpMV,\u201d 2010 IEEE 8th Symposium on Application Specific Processors, pp.64-70, June 2010. 10.1109\/sasp.2010.5521144","DOI":"10.1109\/SASP.2010.5521144"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] B.-Y. Su and K. Keutzer, \u201cclSpMV: A cross-platform OpenCL SpMV framework on GPUs,\u201d Proc. 26th ACM International Conference on Supercomputing, pp.353-364, June 2012. 10.1145\/2304576.2304624","DOI":"10.1145\/2304576.2304624"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] X. Sun, Y. Zhang, T. Wang, G. Long, X. Zhang, and Y. Li, \u201cCRSD: Application specific auto-tuning of SpMV for diagonal sparse matrices,\u201d Euro-Par 2011 Parallel Processing, Lecture Notes in Computer Science, vol.6853, pp.316-327, Springer Berlin Heidelberg, Berlin, Heidelberg, 2011. 10.1007\/978-3-642-23397-5_32","DOI":"10.1007\/978-3-642-23397-5_32"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] N. Thomas, G. Tanase, O. Tkachyshyn, J. Perdue, N.M. Amato, and L. Rauchwerger, \u201cA framework for adaptive algorithm selection in STAPL,\u201d Proc. Tenth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp.277-288, 2005. 10.1145\/1065944.1065981","DOI":"10.1145\/1065944.1065981"},{"key":"28","unstructured":"[28] V.N. Vapnik, Statistical Learning Theory, Wiley-Interscience, Sept. 1998."},{"key":"29","doi-asserted-by":"publisher","unstructured":"[29] R. Vuduc, J.W. Demmel, and K.A. Yelick, \u201cOSKI: A library of automatically tuned sparse matrix kernels,\u201d Journal of Physics: Conference Series, vol.16, no.1, pp.521-530, 2005. 10.1088\/1742-6596\/16\/1\/071","DOI":"10.1088\/1742-6596\/16\/1\/071"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] T. Wu, B. Wang, Y. Shan, F. Yan, Y. Wang, and N. Xu, \u201cEfficient PageRank and SpMV computation on AMD GPUs,\u201d 39th International Conference on Parallel Processing, pp.81-89, 2010. 10.1109\/icpp.2010.17","DOI":"10.1109\/ICPP.2010.17"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] J. Yangqing, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell, \u201cCaffe: Convolutional architecture for fast feature embedding,\u201d Proc. 22nd ACM International Conference on Multimedia, pp.675-678, Nov. 2014.","DOI":"10.1145\/2647868.2654889"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] Y. Zhang, Y.H. Shalabi, R. Jain, K.K. Nagar, and J.D. Bakos, \u201cFPGA vs. GPU for sparse matrix vector multiply,\u201d International Conference on Field-Programmable Technology, pp.255-262, 2009. 10.1109\/fpt.2009.5377620","DOI":"10.1109\/FPT.2009.5377620"},{"key":"33","doi-asserted-by":"publisher","unstructured":"[33] D. Zou, Y. Dou, S. Guo, and S. Ni, \u201cHigh performance sprase matrix-vector multiplication on FPGA,\u201d IEICE Electronics Express, vol.10, no.17, 20130529, 2013. 10.1587\/elex.10.20130529","DOI":"10.1587\/elex.10.20130529"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E101.D\/9\/E101.D_2017EDP7176\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T19:08:05Z","timestamp":1751828885000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E101.D\/9\/E101.D_2017EDP7176\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,1]]},"references-count":33,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2018]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2017edp7176","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,1]]}}}