{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T10:43:59Z","timestamp":1758278639672,"version":"3.37.3"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T00:00:00Z","timestamp":1660176000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T00:00:00Z","timestamp":1660176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s42514-022-00119-7","type":"journal-article","created":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T10:04:11Z","timestamp":1660212251000},"page":"12-25","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["a-Tucker: fast input-adaptive and matricization-free Tucker decomposition of higher-order tensors on GPUs"],"prefix":"10.1007","volume":"5","author":[{"given":"Lian","family":"Duan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanfu","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingshuo","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7426-6248","authenticated-orcid":false,"given":"Chao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,11]]},"reference":[{"key":"119_CR1","doi-asserted-by":"crossref","unstructured":"Ahmad, N., Yilmaz, B., Unat, D.: A prediction framework for fast sparse triangular solves. In: : Malawski M., Rzadca K. (eds) Euro-Par 2020: Parallel Processing. Euro-Par 2020. Lecture Notes in Computer Science, vol. 12247 (2020)","DOI":"10.1007\/978-3-030-57675-2_33"},{"key":"119_CR2","doi-asserted-by":"crossref","unstructured":"Austin, W., Ballard, G., Kolda, T.G.: Parallel tensor compression for large-scale scientific data. In: International Parallel and Distributed Processing Symposium, pp. 912\u2013922 (2016)","DOI":"10.1109\/IPDPS.2016.67"},{"key":"119_CR3","unstructured":"Bader, B.W., Kolda, T.G., et al.: MATLAB Tensor Toolbox Version 3.1. Available online (2019). https:\/\/www.tensortoolbox.org"},{"issue":"1","key":"119_CR4","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1137\/04060593X","volume":"27","author":"J Baglama","year":"2005","unstructured":"Baglama, J., Reichel, L.: Augmented implicitly restarted lanczos bidiagonalization methods. SIAM J. Sci. Comput. 27(1), 19\u201342 (2005)","journal-title":"SIAM J. Sci. Comput."},{"issue":"2","key":"119_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3378445","volume":"46","author":"G Ballard","year":"2020","unstructured":"Ballard, G., Klinvex, A., Kolda, T.G.: TuckerMPI: a parallel C++\/MPI software package for large-scale data compression via the Tucker tensor decomposition. ACM Transact. Math. Softw. 46(2), 1\u201313 (2020)","journal-title":"ACM Transact. Math. Softw."},{"issue":"11","key":"119_CR6","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1007\/s00371-015-1130-y","volume":"32","author":"R Ballester-Ripoll","year":"2016","unstructured":"Ballester-Ripoll, R., Pajarola, R.: Lossy volume compression using tucker truncation and thresholding. Vis. Comput. 32(11), 1433\u20131446 (2016). https:\/\/doi.org\/10.1007\/s00371-015-1130-y","journal-title":"Vis. Comput."},{"key":"119_CR7","doi-asserted-by":"crossref","unstructured":"Benatia, A., Ji, W., Wang, Y., Shi, F.: Sparse matrix format selection with multiclass SVM for SpMV on GPU. In: International Conference on Parallel Processing, pp. 496\u2013505 (2016)","DOI":"10.1109\/ICPP.2016.64"},{"issue":"1","key":"119_CR8","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1017\/S0022112066000545","volume":"24","author":"R Burggraf","year":"1966","unstructured":"Burggraf, R.: Analytical and numerical studies of the structure of steady separated flows. J. Fluid Mech. 24(1), 113\u2013151 (1966)","journal-title":"J. Fluid Mech."},{"key":"119_CR9","doi-asserted-by":"crossref","unstructured":"Chakaravarthy, V.T., Choi, J.W., Joseph, D.J., Liu, X., Murali, P., Sabharwal, Y., Sreedhar, D.: On optimizing distributed Tucker decomposition for dense tensors. In: International Parallel and Distributed Processing Symposium, pp. 1038\u20131047 (2017)","DOI":"10.1109\/IPDPS.2017.86"},{"issue":"4","key":"119_CR10","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1109\/TPDS.2018.2871189","volume":"30","author":"Y Chen","year":"2018","unstructured":"Chen, Y., Li, K., Yang, W., Xiao, G., Xie, X., Li, T.: Performance-aware model for sparse matrix-matrix multiplication on the Sunway TaihuLight supercomputer. IEEE Trans. Parallel Distrib. Syst. 30(4), 923\u2013938 (2018)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"10","key":"119_CR11","doi-asserted-by":"publisher","first-page":"2329","DOI":"10.1109\/TPDS.2020.2990429","volume":"31","author":"Y Chen","year":"2020","unstructured":"Chen, Y., Xiao, G., \u00d6zsu, M.T., Liu, C., Zomaya, A.Y., Li, T.: aeSpTV: an adaptive and efficient framework for sparse tensor-vector product kernel on a high-performance computing platform. IEEE Trans. Parallel Distrib. Syst. 31(10), 2329\u20132345 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"119_CR12","doi-asserted-by":"crossref","unstructured":"Choi, J.W., Liu, X., Chakaravarthy, V.T.: High-performance dense Tucker decomposition on GPU clusters. International Conference for High Performance Computing, Networking, Storage and Analysis, 543\u2013553 (2018)","DOI":"10.1109\/SC.2018.00045"},{"key":"119_CR13","doi-asserted-by":"crossref","unstructured":"Cui, H., Hirasawa, S., Takizawa, H., Kobayashi, H.: A code selection mechanism using deep learning. In: International Symposium on Embedded Multicore\/Many-core Systems-on-Chip, pp. 385\u2013392 (2016)","DOI":"10.1109\/MCSoC.2016.46"},{"key":"119_CR14","doi-asserted-by":"publisher","first-page":"1324","DOI":"10.1137\/S0895479898346995","volume":"21","author":"L De Lathauwer","year":"2000","unstructured":"De Lathauwer, L., De Moor, B., Vandewalle, J.: On the best rank-1 and rank-$$(r_{1}, r_{2}, \\cdots, r_{N})$$ approximation of higher-order tensors. SIAM J. Matrix Anal. Appl. 21, 1324\u20131342 (2000a)","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"4","key":"119_CR15","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1137\/S0895479896305696","volume":"21","author":"L De Lathauwer","year":"2000","unstructured":"De Lathauwer, L., De Moor, B., Vandewalle, J.: A multilinear singular value decomposition. SIAM J. Matrix Anal. Appl. 21(4), 1253\u20131278 (2000b)","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"119_CR16","unstructured":"Dongarra, J., Duff, I., Gates, M., Haidar, A., Hammarling, S., Higham, N.J., Hogg, J., Valero-Lara, P., Relton, S.D., Tomov, S., Zounon, M.: A proposed API for batched basic linear algebra subprograms. Technical report, Manchester Institute for Mathematical Sciences, University of Manchester (2006)"},{"issue":"10","key":"119_CR17","doi-asserted-by":"publisher","first-page":"2359","DOI":"10.1364\/JOSAA.23.002359","volume":"23","author":"D Foster","year":"2006","unstructured":"Foster, D., Amano, K., Nascimento, S., Foster, M.: Frequency of metamerism in natural scenes. Opt. Soc. Am. J. A 23(10), 2359\u20132372 (2006). https:\/\/doi.org\/10.1364\/JOSAA.23.002359","journal-title":"Opt. Soc. Am. J. A"},{"issue":"1","key":"119_CR18","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1137\/S0895479892242232","volume":"16","author":"M Gu","year":"1995","unstructured":"Gu, M., Eisenstat, S.C.: A divide-and-conquer algorithm for the bidiagonal svd. SIAM J. Matrix Anal. Appl. 16(1), 79\u201392 (1995)","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"1\u20134","key":"119_CR19","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1002\/sapm19287139","volume":"7","author":"FL Hitchcock","year":"1928","unstructured":"Hitchcock, F.L.: Multiple invariants and generalized rank of a $$p$$-way matrix or tensor. J. Math. Phys. 7(1\u20134), 39\u201379 (1928)","journal-title":"J. Math. Phys."},{"key":"119_CR20","unstructured":"Hynninen, A.-P., Lyakh, D.I.: cuTT: A high-performance tensor transpose library for CUDA compatible GPUs. arXiv preprint arXiv:1705.01598 (2017)"},{"key":"119_CR21","doi-asserted-by":"crossref","unstructured":"Jang, J., Kang, U.: D-Tucker: Fast and memory-efficient Tucker decomposition for dense tensors. In: International Conference on Data Engineering, pp. 1850\u20131853 (2020)","DOI":"10.1109\/ICDE48307.2020.00186"},{"issue":"2","key":"119_CR22","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1109\/JSTARS.2012.2189200","volume":"5","author":"A Karami","year":"2012","unstructured":"Karami, A., Yazdi, M., Mercier, G.: Compression of hyperspectral images using discerete wavelet transform and Tucker decomposition. J. Sel. Topics Appl. Earth Obs. Remote Sens. 5(2), 444\u2013450 (2012)","journal-title":"J. Sel. Topics Appl. Earth Obs. Remote Sens."},{"key":"119_CR23","doi-asserted-by":"crossref","unstructured":"Kim, Y.-D., Park, E., Yoo, S., Choi, T., Yang, L., Shin, D.: Compression of deep convolutional neural networks for fast and low power mobile applications. arXiv preprint arXiv:1511.06530 (2015)","DOI":"10.14257\/astl.2016.140.36"},{"key":"119_CR24","doi-asserted-by":"crossref","unstructured":"Kim, J., Sukumaran-Rajam, A., Thumma, V., Krishnamoorthy, S., Panyala, A., Pouchet, L., Rountev, A., Sadayappan, P.: A code generator for high-performance tensor contractions on GPUs. In: International Symposium on Code Generation and Optimization, pp. 85\u201395 (2019)","DOI":"10.1109\/CGO.2019.8661182"},{"issue":"3","key":"119_CR25","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1137\/07070111X","volume":"51","author":"TG Kolda","year":"2009","unstructured":"Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455\u2013500 (2009)","journal-title":"SIAM Rev."},{"key":"119_CR26","doi-asserted-by":"crossref","unstructured":"Larsen, R.M.: Lanczos bidiagonalization with partial reorthogonalization. DAIMI Report Series (537) (1998)","DOI":"10.7146\/dpb.v27i537.7070"},{"key":"119_CR27","unstructured":"LeCun, Y., Cortes, C., Burges, C.J.C.: The MNIST database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/ (1998). Accessed 25 Nov 2021"},{"key":"119_CR28","unstructured":"Levin, J.: Three-mode factor analysis. PhD thesis, University of Illinois, Urbana-Champaign (1963)"},{"key":"119_CR33","doi-asserted-by":"crossref","unstructured":"Li, J., Tan, G., Chen, M., Sun, N.: SMAT: An input adaptive auto-tuner for sparse matrix-vector multiplication. In: ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 117\u2013126 (2013)","DOI":"10.1145\/2499370.2462181"},{"issue":"1","key":"119_CR34","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/TPDS.2014.2308221","volume":"26","author":"K Li","year":"2014","unstructured":"Li, K., Yang, W., Li, K.: Performance analysis and optimization for SpMV on GPU using probabilistic modeling. IEEE Trans. Parallel Distrib. Syst. 26(1), 196\u2013205 (2014)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"119_CR29","doi-asserted-by":"crossref","unstructured":"Li, J., Battaglino, C., Perros, I., Sun, J., Vuduc, R.: An input-adaptive and in-place approach to dense tensor-times-matrix multiply. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312 (2015)","DOI":"10.1145\/2807591.2807671"},{"key":"119_CR30","doi-asserted-by":"crossref","unstructured":"Li, J., Choi, J., Perros, I., Sun, J., Vuduc, R.: Model-driven sparse CP decomposition for higher-order tensors. In: International Parallel and Distributed Processing Symposium, pp. 1048\u20131057 (2017)","DOI":"10.1109\/IPDPS.2017.80"},{"key":"119_CR32","doi-asserted-by":"crossref","unstructured":"Li, J., Sun, J., Vuduc, R.: HiCOO: Hierarchical storage of sparse tensors. In: International Conference for High Performance Computing, Networking, Storage, and Analysis, pp. 238\u2013252 (2018)","DOI":"10.1109\/SC.2018.00022"},{"key":"119_CR31","doi-asserted-by":"crossref","unstructured":"Li, J., Ma, Y., Wu, X., Li, A., Barker, K.: PASTA: A parallel sparse tensor algorithm benchmark suite. CCF Transactions on High Performance Computing, 111\u2013130 (2019)","DOI":"10.1007\/s42514-019-00012-w"},{"issue":"7","key":"119_CR35","first-page":"1842","volume":"32","author":"M Li","year":"2020","unstructured":"Li, M., Ao, Y., Yang, C.: Adaptive SpMV\/SpMSpV on GPUs for input vectors of varied sparsity. IEEE Trans. Parallel Distrib. Syst. 32(7), 1842\u20131853 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"119_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10586-011-0179-2","volume":"16","author":"W Ma","year":"2013","unstructured":"Ma, W., Krishamoorthy, S., Villa, O., Kowalski, K., Agrawal, G.: Optimizing tensor contraction expressions for hybrid CPU-GPU execution. Clust. Comput. 16, 1\u201325 (2013)","journal-title":"Clust. Comput."},{"key":"119_CR37","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.jpdc.2018.07.018","volume":"129","author":"Y Ma","year":"2019","unstructured":"Ma, Y., Li, J., Wu, X., Yan, C., Sun, J., Vuduc, R.: Optimizing sparse tensor times matrix on GPUs. J. Parallel Distrib. Comput. 129, 99\u2013109 (2019)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"1","key":"119_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1137\/16M108968X","volume":"40","author":"DA Matthews","year":"2018","unstructured":"Matthews, D.A.: High-performance tensor contraction without transposition. SIAM J. Sci. Comput. 40(1), 1\u201324 (2018)","journal-title":"SIAM J. Sci. Comput."},{"key":"119_CR39","unstructured":"Nico, V., Otto, D., Laurent, S., Barel, M.V., De Lathauwer, L.: Tensorlab 3.0. https:\/\/www.tensorlab.net (2016). Accessed 13 Nov 2021"},{"key":"119_CR40","doi-asserted-by":"crossref","unstructured":"Nisa, I., Li, J., Sukumaran\u00a0Rajam, A., Vuduc, R., Sadayappan, P.: Load-balanced sparse MTTKRP on GPUs. In: International Parallel and Distributed Processing Symposium, pp. 123\u2013133 (2019a)","DOI":"10.1109\/IPDPS.2019.00023"},{"key":"119_CR41","doi-asserted-by":"crossref","unstructured":"Nisa, I., Li, J., Sukumaran-Rajam, A., Rawat, P.S., Krishnamoorthy, S., Sadayappan, P.: An efficient mixed-mode representation of sparse tensors. In: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312 (2019b)","DOI":"10.1145\/3295500.3356216"},{"key":"119_CR42","doi-asserted-by":"crossref","unstructured":"Nisa, I., Siegel, C., Rajam, A.S., Vishnu, A., Sadayappan, P.: Effective machine learning based format selection and performance modeling for SpMV on GPUs. In: International Parallel and Distributed Processing Symposium Workshops, pp. 1056\u20131065 (2018)","DOI":"10.29007\/lnnt"},{"key":"119_CR43","unstructured":"NVIDIA: The API Reference guide for cuBLAS, the CUDA Basic Linear Algebra Subroutine library. in press (2019a). https:\/\/docs.nvidia.com\/cuda\/cublas\/. Accessed 25 Nov 2021"},{"key":"119_CR44","unstructured":"NVIDIA: The API reference guide for cuSolver, the CUDA sparse matix library. in press (2019b). https:\/\/docs.nvidia.com\/cuda\/cusolver\/. Accessed 25 Nov 2021"},{"key":"119_CR46","doi-asserted-by":"crossref","unstructured":"Oh, J., Shin, K., Papalexakis, E.E., Faloutsos, C., Yu, H.: S-HOT: Scalable high-order Tucker decomposition. In: ACM International Conference on Web Search and Data Mining, pp. 761\u2013770 (2017)","DOI":"10.1145\/3018661.3018721"},{"key":"119_CR45","doi-asserted-by":"crossref","unstructured":"Oh, S., Park, N., Sael, L., Kang, U.: Scalable Tucker factorization for sparse tensors - algorithms and discoveries. In: International Conference on Data Engineering, pp. 1120\u20131131 (2018)","DOI":"10.1109\/ICDE.2018.00104"},{"issue":"5","key":"119_CR47","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","volume":"33","author":"IV Oseledetsv","year":"2011","unstructured":"Oseledetsv, I.V.: Tensor-train decomposition. SIAM J. Sci. Comput. 33(5), 2295\u20132317 (2011)","journal-title":"SIAM J. Sci. Comput."},{"key":"119_CR48","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"119_CR49","doi-asserted-by":"crossref","unstructured":"Perros, I., Chen, R., Vuduc, R., Sun, J.: Sparse hierarchical Tucker factorization and its application to healthcare. In: International Conference on Data Mining, pp. 943\u2013948 (2015)","DOI":"10.1109\/ICDM.2015.29"},{"key":"119_CR51","doi-asserted-by":"crossref","unstructured":"Smith, S., Karypis, G.: Tensor-matrix products with a compressed sparse tensor. In: Proceedings of the 5th Workshop on Irregular Applications: Architectures and Algorithms, pp. 1\u20137 (2015)","DOI":"10.1145\/2833179.2833183"},{"key":"119_CR50","doi-asserted-by":"crossref","unstructured":"Smith, S., Karypis, G.: Accelerating the Tucker decomposition with compressed sparse tensors. In: International Conference on Parallel and Distributed Computing, Euro-Par 2017, pp. 653\u2013668 (2017)","DOI":"10.1007\/978-3-319-64203-1_47"},{"key":"119_CR52","doi-asserted-by":"crossref","unstructured":"Springer, P., Su, T., Bientinesi, P.: HPTT: A high-performance tensor transposition C++ library. In: ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming, pp. 56\u201362 (2017)","DOI":"10.1145\/3091966.3091968"},{"key":"119_CR53","doi-asserted-by":"crossref","unstructured":"Sun, J., Tao, D., Faloutsos, C.: Beyond streams and graphs: Dynamic tensor analysis. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 374\u2013383 (2006)","DOI":"10.1145\/1150402.1150445"},{"issue":"2","key":"119_CR54","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1137\/16M1064556","volume":"38","author":"A Szlam","year":"2017","unstructured":"Szlam, A., Tulloch, A., Tygert, M.: Accurate low-rank approximations via a few iterations of alternating least squares. SIAM J. Matrix Anal. Appl. 38(2), 425\u2013433 (2017)","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"119_CR55","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF02289464","volume":"31","author":"LR Tucker","year":"1966","unstructured":"Tucker, L.R.: Some mathematical notes on three-mode factor analysis. Psychometrika 31, 279\u2013311 (1966)","journal-title":"Psychometrika"},{"key":"119_CR56","unstructured":"Vannieuwenhoven, N., Vandebril, R., Meerbergen, K.: On the truncated multilinear singular value decomposition. Technical Report TW589, Department of Computer Science, Katholieke Universiteit Leuven, Leuven, Belgium (2011)"},{"issue":"2","key":"119_CR57","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1137\/110836067","volume":"34","author":"N Vannieuwenhoven","year":"2012","unstructured":"Vannieuwenhoven, N., Vandebril, R., Meerbergen, K.: A new truncation strategy for the higher-order singular value decomposition. SIAM J. Sci. Comput. 34(2), 1027\u20131052 (2012)","journal-title":"SIAM J. Sci. Comput."},{"key":"119_CR58","doi-asserted-by":"crossref","unstructured":"Vedurada, J., Suresh, A., Rajam, A.S., Kim, J., Hong, C., Panyala, A., Krishnamoorthy, S., Nandivada, V.K., Srivastava, R.K., Sadayappan, P.: TTLG-an efficient tensor transposition library for GPUs. In: International Parallel and Distributed Processing Symposium, pp. 578\u2013588 (2018)","DOI":"10.1109\/IPDPS.2018.00067"},{"key":"119_CR59","unstructured":"Vervliet, N., Debals, O., Sorber, L., Barel, M.V., De\u00a0Lathauwer, L.: MATLAB Tensorlab 3.0. Available online (2016). http:\/\/www.tensorlab.net. Accessed 13 Nov 2021"},{"key":"119_CR60","doi-asserted-by":"publisher","unstructured":"Wang, Y., Jodoin, P.-M., Porikli, F., Konrad, J., Benezeth, Y., Ishwar, P.: CDnet 2014: An expanded change detection benchmark dataset. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 393\u2013400 (2014a). https:\/\/doi.org\/10.1109\/CVPRW.2014.126","DOI":"10.1109\/CVPRW.2014.126"},{"key":"119_CR61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-06486-4_7","volume-title":"Intel math kernel library","author":"E Wang","year":"2014","unstructured":"Wang, E., Zhang, Q., Shen, B., Zhang, G., Lu, X., Wu, Q., Wang, Y.: Intel math kernel library. Springer, New York (2014b)"},{"issue":"3","key":"119_CR62","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10915-021-01493-0","volume":"87","author":"C Xiao","year":"2021","unstructured":"Xiao, C., Yang, C., Li, M.: Efficient alternating least squares algorithms for low multilinear rank approximation of tensors. J. Sci. Comput. 87(3), 1\u201325 (2021)","journal-title":"J. Sci. Comput."},{"key":"119_CR63","doi-asserted-by":"crossref","unstructured":"Xie, Z., Tan, G., Liu, W., Sun, N.: IA-SpGEMM: An input-aware auto-tuning framework for parallel sparse matrix-matrix multiplication. In: International Conference on Supercomputing, pp. 94\u2013105 (2019)","DOI":"10.1145\/3330345.3330354"},{"key":"119_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhou, W., Shen, X., Yiu, G.: Overhead-conscious format selection for SpMV-based applications. In: International Parallel and Distributed Processing Symposium, pp. 950\u2013959 (2018a)","DOI":"10.1109\/IPDPS.2018.00104"},{"issue":"1","key":"119_CR65","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1145\/3200691.3178495","volume":"53","author":"Y Zhao","year":"2018","unstructured":"Zhao, Y., Li, J., Liao, C., Shen, X.: Bridging the gap between deep learning and sparse matrix format selection. ACM SIGPLAN Notices 53(1), 94\u2013108 (2018b)","journal-title":"ACM SIGPLAN Notices"},{"key":"119_CR66","volume-title":"Mach. Learn.","author":"Z Zhihua","year":"2016","unstructured":"Zhihua, Z.: Mach. Learn. Tsinghua University Press, Beijing (2016)"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-022-00119-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-022-00119-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-022-00119-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,26]],"date-time":"2023-03-26T21:39:04Z","timestamp":1679866744000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-022-00119-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,11]]},"references-count":66,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["119"],"URL":"https:\/\/doi.org\/10.1007\/s42514-022-00119-7","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"type":"print","value":"2524-4922"},{"type":"electronic","value":"2524-4930"}],"subject":[],"published":{"date-parts":[[2022,8,11]]},"assertion":[{"value":"2 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}