{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T17:10:41Z","timestamp":1769015441156,"version":"3.49.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T00:00:00Z","timestamp":1574208000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T00:00:00Z","timestamp":1574208000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100011347","name":"State Key Laboratory of Software Development Environment","doi-asserted-by":"crossref","award":["SKLSDE-2018ZX-19"],"award-info":[{"award-number":["SKLSDE-2018ZX-19"]}],"id":[{"id":"10.13039\/501100011347","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key R&D Program of China","award":["2016YFB1000503"],"award-info":[{"award-number":["2016YFB1000503"]}]},{"name":"National Key R&D Program of China","award":["2016YFA0602200"],"award-info":[{"award-number":["2016YFA0602200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61502019"],"award-info":[{"award-number":["61502019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61732002"],"award-info":[{"award-number":["61732002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s42514-019-00017-5","type":"journal-article","created":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T15:03:14Z","timestamp":1574262194000},"page":"161-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["swTensor: accelerating tensor decomposition on Sunway architecture"],"prefix":"10.1007","volume":"1","author":[{"given":"Xiaogang","family":"Zhong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-7927","authenticated-orcid":false,"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongzhi","family":"Luan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangwen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Depei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,20]]},"reference":[{"issue":"3","key":"17_CR2","first-page":"187","volume":"36, partii","author":"E Aarts","year":"2007","unstructured":"Aarts, E., Korst, J., Michiels, W.: Simulated annealing. Local Search Combin. Optim. 36, partii(3), 187\u2013210 (2007)","journal-title":"Local Search Combin. Optim."},{"issue":"1","key":"17_CR3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.chemolab.2010.08.004","volume":"106","author":"E Acar","year":"2011","unstructured":"Acar, E., Dunlavy, D.M., Kolda, T.G., M\u00f8rup, M.: Scalable tensor factorizations for incomplete data. Chemometr. Intell. Lab. Syst. 106(1), 41\u201356 (2011)","journal-title":"Chemometr. Intell. Lab. Syst."},{"key":"17_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84882-299-3","volume-title":"Tensors in Image Processing and Computer Vision","author":"S Aja-Fern\u00e1ndez","year":"2009","unstructured":"Aja-Fern\u00e1ndez, S., de Luis Garcia, R., Tao, D., Li, X.: Tensors in Image Processing and Computer Vision. Springer, Berlin (2009)"},{"issue":"1","key":"17_CR5","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1214\/ss\/1177011077","volume":"8","author":"D Bertsimas","year":"1993","unstructured":"Bertsimas, D., Tsitsiklis, J.: Simulated annealing. Stat. Sci. 8(1), 10\u201315 (1993)","journal-title":"Stat. Sci."},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Beutel, A., Talukdar, P.P., Kumar, A., Faloutsos, C., Papalexakis, E.E., Xing, E.P.: Flexifact: scalable flexible factorization of coupled tensors on hadoop. In: Proceedings of the 2014 SIAM International Conference on Data Mining, pp. 109\u2013117. SIAM (2014)","DOI":"10.1137\/1.9781611973440.13"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Blanco, Z., Liu, B., Dehnavi, M.M.: Cstf: Large-scale sparse tensor factorizations on distributed platforms. In: Proceedings of the 47th International Conference on Parallel Processing, p.\u00a021. ACM (2018)","DOI":"10.1145\/3225058.3225133"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chang, K.W., Yih, S.W.t., Yang, B., Meek, C.: Typed tensor decomposition of knowledge bases for relation extraction (2014)","DOI":"10.3115\/v1\/D14-1165"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Chen, B., Fu, H., Wei, Y., He, C., Zhang, W., Li, Y., Wan, W., Zhang, W., Gan, L., Zhang, W., et\u00a0al.: Simulating the Wenchuan earthquake with accurate surface topography on Sunway taihulight. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, p.\u00a040. IEEE Press (2018)","DOI":"10.1109\/SC.2018.00043"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Choi, J., Liu, X., Smith, S., Simon, T.: Blocking optimization techniques for sparse tensor computation. In: 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 568\u2013577. IEEE (2018)","DOI":"10.1109\/IPDPS.2018.00066"},{"key":"17_CR11","first-page":"1296","volume":"2","author":"JH Choi","year":"2014","unstructured":"Choi, J.H., Vishwanathan, S.V.N.: Dfacto: distributed factorization of tensors. Adv. Neural Inf. Process. Syst. 2, 1296\u20131304 (2014)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"17_CR12","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/MSP.2013.2297439","volume":"32","author":"A Cichocki","year":"2015","unstructured":"Cichocki, A., Mandic, D., De Lathauwer, L., Zhou, G., Zhao, Q., Caiafa, C., Phan, H.A.: Tensor decompositions for signal processing applications: from two-way to multiway component analysis. IEEE Signal Process. Mag. 32(2), 145\u2013163 (2015)","journal-title":"IEEE Signal Process. Mag."},{"issue":"1","key":"17_CR13","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Duan, X., Gao, P., Zhang, T., Zhang, M., Liu, W., Zhang, W., Xue, W., Fu, H., Gan, L., Chen, D., et\u00a0al.: Redesigning lammps for peta-scale and hundred-billion-atom simulation on sunway taihulight. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, p.\u00a012. IEEE Press (2018)","DOI":"10.1109\/SC.2018.00015"},{"key":"17_CR15","volume-title":"Matrix Computations","author":"GH Golub","year":"2012","unstructured":"Golub, G.H., Van Loan, C.F.: Matrix Computations, vol. 3. JHU Press, Baltimore (2012)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Han, Q., Yang, H., Luan, Z., Qian, D.: Accelerating tile low-rank gemm on Sunway architecture: Poster. In: Proceedings of the 16th ACM International Conference on Computing Frontiers, pp. 295\u2013297. ACM (2019)","DOI":"10.1145\/3310273.3323425"},{"issue":"4","key":"17_CR17","first-page":"19","volume":"5","author":"FM Harper","year":"2016","unstructured":"Harper, F.M., Konstan, J.A.: The movielens datasets: history and context. ACM Trans. Interact. Intell. Syst. (tiis) 5(4), 19 (2016)","journal-title":"ACM Trans. Interact. Intell. Syst. (tiis)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, H., Kan, M.Y., Chua, T.S.: Fast matrix factorization for online recommendation with implicit feedback. In: Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, pp. 549\u2013558. ACM (2016)","DOI":"10.1145\/2911451.2911489"},{"issue":"1\u20134","key":"17_CR19","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1002\/sapm192761164","volume":"6","author":"FL Hitchcock","year":"1927","unstructured":"Hitchcock, F.L.: The expression of a tensor or a polyadic as a sum of products. J. Math. Phys. 6(1\u20134), 164\u2013189 (1927)","journal-title":"J. Math. Phys."},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Hu, Y., Yang, H., Luan, Z., Qian, D.: Massively scaling seismic processing on sunway taihulight supercomputer. arXiv preprint arXiv:1907.11678 (2019)","DOI":"10.1109\/TPDS.2019.2962395"},{"issue":"4","key":"17_CR21","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/s00778-016-0427-4","volume":"25","author":"I Jeon","year":"2016","unstructured":"Jeon, I., Papalexakis, E.E., Faloutsos, C., Sael, L., Kang, U.: Mining billion-scale tensors: algorithms and discoveries. Int. J. Very Large Data Bases 25(4), 519\u2013544 (2016)","journal-title":"Int. J. Very Large Data Bases"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Jeon, I., Papalexakis, E.E., Kang, U., Faloutsos, C.: Haten2: Billion-scale tensor decompositions. In: Data Engineering (ICDE), 2015 IEEE 31st International Conference on, pp. 1047\u20131058. IEEE (2015)","DOI":"10.1109\/ICDE.2015.7113355"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Kang, U., Papalexakis, E., Harpale, A., Faloutsos, C.: Gigatensor: scaling tensor analysis up by 100 times-algorithms and discoveries. In: Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 316\u2013324. ACM (2012)","DOI":"10.1145\/2339530.2339583"},{"issue":"3","key":"17_CR24","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."},{"issue":"9","key":"17_CR25","doi-asserted-by":"publisher","first-page":"2473","DOI":"10.1109\/TIP.2006.877438","volume":"15","author":"C Lei","year":"2006","unstructured":"Lei, C., Yang, Y.H.: Tri-focal tensor-based multiple video synchronization with subframe optimization. IEEE Trans. Image Process. 15(9), 2473\u20132480 (2006)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Ma, Y., Yan, C., Vuduc, R.: Optimizing sparse tensor times matrix on multi-core and many-core architectures. In: Proceedings of the Sixth Workshop on Irregular Applications: Architectures and Algorithms, pp. 26\u201333. IEEE Press (2016)","DOI":"10.1109\/IA3.2016.010"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Li, L., Yu, T., Zhao, W., Fu, H., Wang, C., Tan, L., Yang, G., Thomson, J.: Large-scale hierarchical k-means for heterogeneous many-core supercomputers. In: SC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 160\u2013170. IEEE (2018a)","DOI":"10.1109\/SC.2018.00016"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Li, M., Liu, Y., Yang, H., Luan, Z., Qian, D.: Multi-role sptrsv on sunway many-core architecture. In: 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 594\u2013601. IEEE (2018b)","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00109"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Lim, L.H., Comon, P.: Multiarray signal processing: Tensor decomposition meets compressed sensing. arXiv preprint arXiv:1002.4935 (2010)","DOI":"10.1016\/j.crme.2010.06.005"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Liu, B., Wen, C., Sarwate, A.D., Dehnavi, M.M.: A unified optimization approach for sparse tensor operations on gpus. In: 2017 IEEE International Conference on Cluster Computing (CLUSTER), pp. 47\u201357. IEEE (2017)","DOI":"10.1109\/CLUSTER.2017.75"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Liu, C., Xie, B., Liu, X., Xue, W., Yang, H., Liu, X.: Towards efficient spmv on sunway manycore architectures. In: Proceedings of the 2018 International Conference on Supercomputing, pp. 363\u2013373. ACM (2018)","DOI":"10.1145\/3205289.3205313"},{"key":"17_CR32","unstructured":"Liu, C., Yang, H., Sun, R., Luan, Z., Qian, D.: swtvm: Exploring the automated compilation for deep learning on sunway architecture. arXiv preprint arXiv:1904.07404 (2019)"},{"key":"17_CR33","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."},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Nickel, M., Tresp, V., Kriegel, H.P.: Factorizing yago: scalable machine learning for linked data. In: Proceedings of the 21st international conference on World Wide Web, pp. 271\u2013280. ACM (2012)","DOI":"10.1145\/2187836.2187874"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Nisa, I., Li, J., Sukumaran-Rajam, A., Vuduc, R., Sadayappan, P.: Load-balanced sparse mttkrp on gpus. arXiv preprint arXiv:1904.03329 (2019)","DOI":"10.1109\/IPDPS.2019.00023"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Oh, S., Park, N., Jang, J.G., Sael, L., Kang, U.: High-performance tucker factorization on heterogeneous platforms. IEEE Trans. Parallel Distrib. Syst. (2019)","DOI":"10.1109\/TPDS.2019.2908639"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Park, N., Jeon, B., Lee, J., Kang, U.: Bigtensor: Mining billion-scale tensor made easy. In: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, pp. 2457\u20132460. ACM (2016)","DOI":"10.1145\/2983323.2983332"},{"issue":"3","key":"17_CR38","doi-asserted-by":"publisher","first-page":"C269","DOI":"10.1137\/18M1210691","volume":"41","author":"ET Phipps","year":"2019","unstructured":"Phipps, E.T., Kolda, T.G.: Software for sparse tensor decomposition on emerging computing architectures. SIAM J. Sci. Comput. 41(3), C269\u2013C290 (2019)","journal-title":"SIAM J. Sci. Comput."},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Shashua, A., Hazan, T.: Non-negative tensor factorization with applications to statistics and computer vision. In: Proceedings of the 22nd international conference on Machine learning, pp. 792\u2013799. ACM (2005)","DOI":"10.1145\/1102351.1102451"},{"issue":"13","key":"17_CR40","doi-asserted-by":"publisher","first-page":"3551","DOI":"10.1109\/TSP.2017.2690524","volume":"65","author":"ND Sidiropoulos","year":"2017","unstructured":"Sidiropoulos, N.D., De Lathauwer, L., Fu, X., Huang, K., Papalexakis, E.E., Faloutsos, C.: Tensor decomposition for signal processing and machine learning. IEEE Trans. Signal Process. 65(13), 3551\u20133582 (2017)","journal-title":"IEEE Trans. Signal Process."},{"key":"17_CR41","unstructured":"Smith, S., Choi, J.W., Li, J., Vuduc, R., Park, J., Liu, X., Karypis, G.: Frostt: The formidable repository of open sparse tensors and tools (2017)"},{"key":"17_CR42","unstructured":"Smith, S., Park, J., Karypis, G.: Sparse tensor factorization on many-core processors with high-bandwidth memory. In: Parallel and Distributed Processing Symposium (IPDPS), 2017 IEEE International, pp. 1058\u20131067. IEEE (2017)"},{"key":"17_CR43","unstructured":"Sonka, M., Hlavac, V., Boyle, R.: Image processing, analysis, and machine vision. Cengage Learning (2014)"},{"key":"17_CR44","unstructured":"Tew, P.A.: An investigation of sparse tensor formats for tensor libraries. Ph.D. thesis, Massachusetts Institute of Technology (2016)"},{"key":"17_CR45","unstructured":"Tsourakakis, C.E.: Data mining with mapreduce: Graph and tensor algorithms with applications. Diss. Master\u2019s thesis, Carnegie Mellon University (2010)"},{"key":"17_CR46","first-page":"122","volume":"15","author":"LR Tucker","year":"1963","unstructured":"Tucker, L.R.: Implications of factor analysis of three-way matrices for measurement of change. Probl. Meas. Change 15, 122\u2013137 (1963)","journal-title":"Probl. Meas. Change"},{"issue":"1","key":"17_CR47","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1145\/3200691.3178513","volume":"53","author":"Xinliang Wang","year":"2018","unstructured":"Wang, X., Xue, W., Liu, W., Wu, L.: swsptrsv: a fast sparse triangular solve with sparse level tile layout on sunway architectures. In: Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 338\u2013353. ACM (2018)","journal-title":"ACM SIGPLAN Notices"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: An insightful visual performance model for floating-point programs and multicore architectures. Tech. rep., Lawrence Berkeley National Lab.(LBNL), Berkeley (2009)","DOI":"10.2172\/1407078"},{"key":"17_CR49","unstructured":"Xu, Z., Lin, J., Matsuoka, S.: Benchmarking sw26010 many-core processor. In: Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2017 IEEE International, pp. 743\u2013752. IEEE (2017)"},{"key":"17_CR1","unstructured":"Yelp dataset challenge. (2019) https:\/\/www.yelp.com\/dataset\/challenge"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Zhong, X., Li, M., Yang, H., Liu, Y., Qian, D.: swmr: A framework for accelerating mapreduce applications on sunway taihulight. IEEE Trans. Emerg. Topics Comput. (2018)","DOI":"10.1109\/TETC.2018.2881265"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-019-00017-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s42514-019-00017-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-019-00017-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T12:01:33Z","timestamp":1665057693000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s42514-019-00017-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,20]]},"references-count":50,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["17"],"URL":"https:\/\/doi.org\/10.1007\/s42514-019-00017-5","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,20]]},"assertion":[{"value":"9 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}