{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T08:27:14Z","timestamp":1761294434905,"version":"3.37.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002186"],"award-info":[{"award-number":["62002186"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["ZR2019PF015"],"award-info":[{"award-number":["ZR2019PF015"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"crossref"}]},{"name":"\u201cColleges and Universities 20 Terms\u201d Foundation of Jinan City, China","award":["2018GXRC015"],"award-info":[{"award-number":["2018GXRC015"]}]},{"name":"Research and Application Demonstration of Key Technologies of Autonomous Controllable Supercomputing Software Ecosystem Project","award":["2020KJC-ZD01"],"award-info":[{"award-number":["2020KJC-ZD01"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s11227-021-04270-w","type":"journal-article","created":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T10:10:42Z","timestamp":1644574242000},"page":"11441-11463","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["swSuperLU: A highly scalable sparse direct solver on Sunway manycore architecture"],"prefix":"10.1007","volume":"78","author":[{"given":"Min","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zanjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingshan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,11]]},"reference":[{"key":"4270_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544631","volume-title":"Field Computation by Moment Methods","author":"RF Harrington","year":"1993","unstructured":"Harrington RF (1993) Field Computation by Moment Methods. Wiley-IEEE Press, Hoboken"},{"key":"4270_CR2","volume-title":"Theory and computation of electromagnetic fields","author":"JM Jin","year":"2011","unstructured":"Jin JM (2011) Theory and computation of electromagnetic fields. John Wiley & Sons, Hoboken"},{"key":"4270_CR3","volume-title":"Multiphase fluid flow in porous and fractured reservoirs","author":"YS Wu","year":"2015","unstructured":"Wu YS (2015) Multiphase fluid flow in porous and fractured reservoirs. Gulf professional publishing, Oxford"},{"key":"4270_CR4","volume-title":"Computational fluid dynamics: principles and applications","author":"J Blazek","year":"2015","unstructured":"Blazek J (2015) Computational fluid dynamics: principles and applications. Butterworth-Heinemann, Oxford"},{"key":"4270_CR5","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718881","volume-title":"Direct methods for sparse linear systems","author":"TA Davis","year":"2006","unstructured":"Davis TA (2006) Direct methods for sparse linear systems. SIAM, Philadelphia"},{"key":"4270_CR6","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718003","volume-title":"Iterative methods for sparse linear systems","author":"Y Saad","year":"2003","unstructured":"Saad Y (2003) Iterative methods for sparse linear systems. SIAM, Philadelphia"},{"issue":"3","key":"4270_CR7","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1137\/S0895479895291765","volume":"20","author":"JW Demmel","year":"1999","unstructured":"Demmel JW, Eisenstat SC, Gilbert JR, Li XS, Liu JW (1999) A supernodal approach to sparse partial pivoting. SIAM J Matrix Anal Appl 20(3):720\u2013755","journal-title":"SIAM J Matrix Anal Appl"},{"issue":"2","key":"4270_CR8","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1137\/0614024","volume":"14","author":"JR Gilbert","year":"1993","unstructured":"Gilbert JR, Liu JW (1993) Elimination structures for unsymmetric sparse lu factors. SIAM J Matrix Anal Appl 14(2):334\u2013352","journal-title":"SIAM J Matrix Anal Appl"},{"issue":"2","key":"4270_CR9","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1145\/567806.567807","volume":"28","author":"LS Blackford","year":"2002","unstructured":"Blackford LS, Petitet A, Pozo R, Remington K, Whaley RC, Demmel J, Dongarra J, Duff I, Hammarling S, Henry G et al (2002) An updated set of basic linear algebra subprograms (blas). ACM Trans Math Softw 28(2):135\u2013151","journal-title":"ACM Trans Math Softw"},{"issue":"7","key":"4270_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-016-5588-7","volume":"59","author":"H Fu","year":"2016","unstructured":"Fu H, Liao J, Yang J, Wang L, Song Z, Huang X, Yang C, Xue W, Liu F, Qiao F et al (2016) The sunway taihulight supercomputer: system and applications. Sci China Inform Sci 59(7):1\u201316","journal-title":"Sci China Inform Sci"},{"key":"4270_CR11","doi-asserted-by":"crossref","unstructured":"Liu Y, Jacquelin M, Ghysels P, Li XS (2018) Highly scalable distributed-memory sparse triangular solution algorithms. In: 2018 Proceedings of the Seventh SIAM Workshop on Combinatorial Scientific Computing, pp. 87\u201396. SIAM","DOI":"10.1137\/1.9781611975215.9"},{"key":"4270_CR12","doi-asserted-by":"crossref","unstructured":"Yamazaki I, Li XS (2012) New scheduling strategies and hybrid programming for a parallel right-looking sparse lu factorization algorithm on multicore cluster systems. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium, pp. 619\u2013630. IEEE","DOI":"10.1109\/IPDPS.2012.63"},{"key":"4270_CR13","doi-asserted-by":"crossref","unstructured":"Sao P, Li XS, Vuduc R (2018) A communication-avoiding 3d lu factorization algorithm for sparse matrices. In: 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 908\u2013919. IEEE","DOI":"10.1109\/IPDPS.2018.00100"},{"key":"4270_CR14","doi-asserted-by":"crossref","unstructured":"Sao P, Vuduc R, Li XS (2014) A distributed cpu-gpu sparse direct solver. In: European Conference on Parallel Processing, pp. 487\u2013498. Springer","DOI":"10.1007\/978-3-319-09873-9_41"},{"key":"4270_CR15","doi-asserted-by":"crossref","unstructured":"Sao P, Liu X, Vuduc R, Li X (2015) A sparse direct solver for distributed memory xeon phi-accelerated systems. In: 2015 IEEE International Parallel and Distributed Processing Symposium, pp. 71\u201381. IEEE","DOI":"10.1109\/IPDPS.2015.104"},{"key":"4270_CR16","doi-asserted-by":"crossref","unstructured":"Niu Y, Lu Z, Dong M, Jin Z, Liu W, Tan G (2021) Tilespmv: A tiled algorithm for sparse matrix-vector multiplication on gpus. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 68\u201378. IEEE","DOI":"10.1109\/IPDPS49936.2021.00016"},{"key":"4270_CR17","doi-asserted-by":"crossref","unstructured":"Su J, Zhang F, Liu W, He B, Wu R, Du X, Wang R (2020) Capellinisptrsv: A thread-level synchronization-free sparse triangular solve on gpus. In: 49th International Conference on Parallel Processing-ICPP, pp. 1\u201311","DOI":"10.1145\/3404397.3404400"},{"key":"4270_CR18","doi-asserted-by":"crossref","unstructured":"Lu Z, Niu Y, Liu W (2020) Efficient block algorithms for parallel sparse triangular solve. In: 49th International Conference on Parallel Processing-ICPP, pp. 1\u201311","DOI":"10.1145\/3404397.3404413"},{"key":"4270_CR19","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 al (2018) Redesigning lammps for peta-scale and hundred-billion-atom simulation on sunway taihulight. In: SC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 148\u2013159. IEEE","DOI":"10.1109\/SC.2018.00015"},{"key":"4270_CR20","doi-asserted-by":"crossref","unstructured":"Chen B, Fu H, Wei Y, He C, Zhang W, Li Y, Wan W, Zhang W, Gan L, Zhang Z et al (2018) Simulating the wenchuan earthquake with accurate surface topography on sunway taihulight. In: SC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 517\u2013528. IEEE","DOI":"10.1109\/SC.2018.00043"},{"key":"4270_CR21","doi-asserted-by":"crossref","unstructured":"Fu H, Liao J, Ding N, Duan X, Gan L, Liang Y, Wang X, Yang J, Zheng Y, Liu W et al (2017) Redesigning cam-se for peta-scale climate modeling performance and ultra-high resolution on sunway taihulight. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312","DOI":"10.1145\/3126908.3126909"},{"key":"4270_CR22","doi-asserted-by":"crossref","unstructured":"Lin H, Zhu X, Yu B, Tang X, Xue W, Chen W, Zhang L, Hoefler T, Ma X, Liu X et al (2018)Shentu: processing multi-trillion edge graphs on millions of cores in seconds. In: SC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 706\u2013716. IEEE","DOI":"10.1109\/SC.2018.00059"},{"key":"4270_CR23","unstructured":"Zhong X, Li M, Yang H, Liu Y, Qian D (2018) swmr: a framework for accelerating mapreduce applications on sunway taihulight. IEEE Transactions on Emerging Topics in Computing"},{"key":"4270_CR24","doi-asserted-by":"crossref","unstructured":"Li L, Fang J, Fu H, Jiang J, Zhao W, He C, You X, Yang G (2018) swcaffe: A parallel framework for accelerating deep learning applications on sunway taihulight. In: 2018 IEEE International Conference on Cluster Computing (CLUSTER), pp. 413\u2013422. IEEE","DOI":"10.1109\/CLUSTER.2018.00087"},{"key":"4270_CR25","doi-asserted-by":"crossref","unstructured":"Liu C, Xie B, Liu X, Xue W, Yang H, Liu X (2018) Towards efficient spmv on sunway manycore architectures. In: Proceedings of the 2018 International Conference on Supercomputing, pp. 363\u2013373","DOI":"10.1145\/3205289.3205313"},{"key":"4270_CR26","doi-asserted-by":"crossref","unstructured":"Li M, Liu Y, Yang H, Luan Z, Qian D (2018) 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","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00109"},{"key":"4270_CR27","doi-asserted-by":"crossref","unstructured":"Wang X, Liu W, Xue W, Wu L (2018) 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","DOI":"10.1145\/3178487.3178513"},{"key":"4270_CR28","doi-asserted-by":"crossref","unstructured":"Fang J, Fu H, Zhao W, Chen B, Zheng W, Yang G (2017) swdnn: A library for accelerating deep learning applications on sunway taihulight. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 615\u2013624. IEEE","DOI":"10.1109\/IPDPS.2017.20"},{"issue":"7","key":"4270_CR29","doi-asserted-by":"publisher","first-page":"1636","DOI":"10.1109\/TPDS.2019.2953852","volume":"31","author":"M Li","year":"2019","unstructured":"Li M, Liu Y, Yang H, Luan Z, Gan L, Yang G, Qian D (2019) Accelerating sparse cholesky factorization on sunway manycore architecture. IEEE Trans Parallel Distrib Syst 31(7):1636\u20131650","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"1","key":"4270_CR30","first-page":"1","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis TA, Hu Y (2011) The university of florida sparse matrix collection. ACM Trans Math Softw (TOMS) 38(1):1\u201325","journal-title":"ACM Trans Math Softw (TOMS)"},{"issue":"2","key":"4270_CR31","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1137\/0205021","volume":"5","author":"DJ Rose","year":"1976","unstructured":"Rose DJ, Tarjan RE, Lueker GS (1976) Algorithmic aspects of vertex elimination on graphs. SIAM J Comput 5(2):266\u2013283","journal-title":"SIAM J Comput"},{"issue":"1","key":"4270_CR32","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1137\/0134014","volume":"34","author":"DJ Rose","year":"1978","unstructured":"Rose DJ, Tarjan RE (1978) Algorithmic aspects of vertex elimination on directed graphs. SIAM J Appl Math 34(1):176\u2013197","journal-title":"SIAM J Appl Math"},{"issue":"3","key":"4270_CR33","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1137\/0601033","volume":"1","author":"JR Gilbert","year":"1980","unstructured":"Gilbert JR (1980) A note on the np-completeness of vertex elimination on directed graphs. SIAM J Algebraic Discrete Methods 1(3):292\u2013294","journal-title":"SIAM J Algebraic Discrete Methods"},{"issue":"1","key":"4270_CR34","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1137\/0602010","volume":"2","author":"M Yannakakis","year":"1981","unstructured":"Yannakakis M (1981) Computing the minimum fill-in is np-complete. SIAM J Algeb Discrete Methods 2(1):77\u201379","journal-title":"SIAM J Algeb Discrete Methods"},{"issue":"11","key":"4270_CR35","doi-asserted-by":"publisher","first-page":"1801","DOI":"10.1109\/PROC.1967.6011","volume":"55","author":"WF Tinney","year":"1967","unstructured":"Tinney WF, Walker JW (1967) Direct solutions of sparse network equations by optimally ordered triangular factorization. Proc IEEE 55(11):1801\u20131809","journal-title":"Proc IEEE"},{"key":"4270_CR36","first-page":"183","volume-title":"A graph-theoretic study of the numerical solution of sparse positive definite systems of linear equations In Graph Theory and Computing","author":"DJ Rose","year":"1972","unstructured":"Rose DJ (1972) A graph-theoretic study of the numerical solution of sparse positive definite systems of linear equations In Graph Theory and Computing. Elsevier, New York, pp 183\u2013217"},{"issue":"4","key":"4270_CR37","doi-asserted-by":"publisher","first-page":"886","DOI":"10.1137\/S0895479894278952","volume":"17","author":"PR Amestoy","year":"1996","unstructured":"Amestoy PR, Davis TA, Duff IS (1996) An approximate minimum degree ordering algorithm. SIAM J Matrix Anal Appl 17(4):886\u2013905","journal-title":"SIAM J Matrix Anal Appl"},{"issue":"2","key":"4270_CR38","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1137\/0902019","volume":"2","author":"SC Eisenstat","year":"1981","unstructured":"Eisenstat SC, Schultz MH, Sherman AH (1981) Algorithms and data structures for sparse symmetric gaussian elimination. SIAM J Sc Statist Comput 2(2):225\u2013237","journal-title":"SIAM J Sc Statist Comput"},{"issue":"2","key":"4270_CR39","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1145\/214392.214398","volume":"11","author":"JW Liu","year":"1985","unstructured":"Liu JW (1985) Modification of the minimum-degree algorithm by multiple elimination. ACM Trans Math Softw (TOMS) 11(2):141\u2013153","journal-title":"ACM Trans Math Softw (TOMS)"},{"issue":"1","key":"4270_CR40","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1137\/S1064827595287997","volume":"20","author":"G Karypis","year":"1998","unstructured":"Karypis G, Kumar V (1998) A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J Sci Comput 20(1):359\u2013392","journal-title":"SIAM J Sci Comput"},{"issue":"1","key":"4270_CR41","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1006\/jpdc.1997.1404","volume":"48","author":"G Karypis","year":"1998","unstructured":"Karypis G, Kumar V (1998) Multilevelk-way partitioning scheme for irregular graphs. J Parallel Distrib Comput 48(1):96\u2013129","journal-title":"J Parallel Distrib Comput"},{"key":"4270_CR42","doi-asserted-by":"crossref","unstructured":"Karypis G, Kumar V (1998) Multilevel algorithms for multi-constraint graph partitioning. In: SC\u201998: Proceedings of the 1998 ACM\/IEEE Conference on Supercomputing, pp. 28\u201328. IEEE","DOI":"10.1109\/SC.1998.10018"},{"key":"4270_CR43","unstructured":"Karypis G, Kumar V (1997) A coarse-grain parallel formulation of multilevel k-way graph partitioning algorithm. In: PPSC"},{"key":"4270_CR44","doi-asserted-by":"crossref","unstructured":"Schloegel K, Karypis G, Kumar V (2000) Parallel multilevel algorithms for multi-constraint graph partitioning. In: European Conference on Parallel Processing, pp. 296\u2013310. Springer","DOI":"10.1007\/3-540-44520-X_39"},{"key":"4270_CR45","doi-asserted-by":"crossref","unstructured":"Cuthill E, McKee J (1969) Reducing the bandwidth of sparse symmetric matrices. In: Proceedings of the 1969 24th National Conference, pp. 157\u2013172","DOI":"10.1145\/800195.805928"},{"key":"4270_CR46","volume-title":"Computer solution of large sparse positive definite","author":"A George","year":"1981","unstructured":"George A, Liu JW (1981) Computer solution of large sparse positive definite. Prentice Hall Professional Technical Reference, Englewood Cliffs"},{"issue":"2","key":"4270_CR47","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1145\/779359.779361","volume":"29","author":"XS Li","year":"2003","unstructured":"Li XS, Demmel JW (2003) Superlu\\_dist: a scalable distributed-memory sparse direct solver for unsymmetric linear systems. ACM Trans Math Softw (TOMS) 29(2):110\u2013140","journal-title":"ACM Trans Math Softw (TOMS)"},{"issue":"1","key":"4270_CR48","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1137\/S0895479899358194","volume":"23","author":"PR Amestoy","year":"2001","unstructured":"Amestoy PR, Duff IS, L\u2019Excellent J-Y, Koster J (2001) A fully asynchronous multifrontal solver using distributed dynamic scheduling. SIAM J Matrix Anal Appl 23(1):15\u201341","journal-title":"SIAM J Matrix Anal Appl"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-021-04270-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-021-04270-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-021-04270-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,19]],"date-time":"2022-05-19T10:23:21Z","timestamp":1652955801000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-021-04270-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,11]]},"references-count":48,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["4270"],"URL":"https:\/\/doi.org\/10.1007\/s11227-021-04270-w","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2022,2,11]]},"assertion":[{"value":"20 December 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}