{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,2,18]],"date-time":"2024-02-18T00:11:19Z","timestamp":1708215079991},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T00:00:00Z","timestamp":1695081600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T00:00:00Z","timestamp":1695081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s11227-023-05641-1","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T04:02:27Z","timestamp":1695096147000},"page":"4682-4706","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["swPTS: an efficient parallel Thomas split algorithm for tridiagonal systems on Sunway manycore processors"],"prefix":"10.1007","volume":"80","author":[{"given":"Min","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingshan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Gou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zanjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,19]]},"reference":[{"key":"5641_CR1","unstructured":"Lefohn A, Davis UC, Owens J, Davis UC (2006) Interactive depth of field using simulated diffusion. Pixar Animation Studios Tech Report"},{"key":"5641_CR2","unstructured":"Sengupta S, Harris M, Yao Z, Owens J.D (2007) Scan primitives for gpu computing. In: Proceedings of the 22nd ACM SIGGRAPH\/EUROGRAPHICS Symposium on Graphics Hardware"},{"issue":"2","key":"5641_CR3","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/0021-9991(85)90148-2","volume":"59","author":"J Kim","year":"1985","unstructured":"Kim J, Moin P (1985) Application of a fractional-step method to incompressible navier-stokes equations. J Comput Phys 59(2):308\u2013323","journal-title":"J Comput Phys"},{"key":"5641_CR4","doi-asserted-by":"crossref","unstructured":"Kass M, Miller G (1990) Rapid, stable fluid dynamics for computer graphics. In: Proceedings of the 17th Annual Conference on Computer Graphics and Interactive Techniques, pp 49\u201357","DOI":"10.1145\/97879.97884"},{"issue":"6","key":"5641_CR5","doi-asserted-by":"publisher","DOI":"10.1115\/1.4023858","volume":"135","author":"S Vanka","year":"2013","unstructured":"Vanka S (2013) 2012 freeman scholar lecture: computational fluid dynamics on graphics processing units. J Fluids Eng 135(6):061401","journal-title":"J Fluids Eng"},{"issue":"7","key":"5641_CR6","doi-asserted-by":"publisher","first-page":"1886","DOI":"10.1016\/j.cpc.2014.03.014","volume":"185","author":"WC Tay","year":"2014","unstructured":"Tay WC, Tan EL (2014) Pentadiagonal alternating-direction-implicit finite-difference time-domain method for two-dimensional schr\u00f6dinger equation. Comput Phys Commun 185(7):1886\u20131892","journal-title":"Comput Phys Commun"},{"key":"5641_CR7","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.cpc.2014.10.008","volume":"187","author":"LZ Li","year":"2015","unstructured":"Li LZ, Sun H-W, Tam S-C (2015) A spatial sixth-order alternating direction implicit method for two-dimensional cubic nonlinear schr\u00f6dinger equations. Comput Phys Commun 187:38\u201348","journal-title":"Comput Phys Commun"},{"key":"5641_CR8","doi-asserted-by":"crossref","unstructured":"Egloff D (2012) Chapter 23 - pricing financial derivatives with high performance finite difference solvers on gpus. In: Hwu, W.-m.W. (eds.) GPU Computing Gems Jade Edition. Applications of GPU Computing Series, pp. 309\u2013322. Morgan Kaufmann, Boston","DOI":"10.1016\/B978-0-12-385963-1.00023-X"},{"issue":"2","key":"5641_CR9","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.parco.2006.11.002","volume":"33","author":"H Sak","year":"2007","unstructured":"Sak H, \u00d6zekici S (2007) \u0130lkay Bodurog$$^{\\sim }$$lu: parallel computing in Asian option pricing. Parallel Comput 33(2):92\u2013108","journal-title":"Parallel Comput"},{"issue":"4","key":"5641_CR10","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1134\/S2070048214040103","volume":"6","author":"VT Zhukov","year":"2014","unstructured":"Zhukov VT, Novikova ND, Feodoritova OB (2014) Parallel multigrid method for solving elliptic equations. Math Models Comput Simul 6(4):425\u2013434","journal-title":"Math Models Comput Simul"},{"issue":"1","key":"5641_CR11","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/TPDS.2010.61","volume":"22","author":"D G\u00f6ddeke","year":"2010","unstructured":"G\u00f6ddeke D, Strzodka R (2010) Cyclic reduction tridiagonal solvers on gpus applied to mixed-precision multigrid. IEEE Trans Parallel Distrib Syst 22(1):22\u201332","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"2","key":"5641_CR12","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1145\/355945.355947","volume":"7","author":"H Wang","year":"1981","unstructured":"Wang H (1981) A parallel method for tridiagonal equations. ACM Trans Math Softw (TOMS) 7(2):170\u2013183","journal-title":"ACM Trans Math Softw (TOMS)"},{"key":"5641_CR13","doi-asserted-by":"crossref","unstructured":"Li F, Liu X, Liu Y, Zhao P, Yang Y, Shang H, Sun W, Wang Z, Dong E, Chen D (2021) Sw_qsim: A minimize-memory quantum simulator with high-performance on a new sunway supercomputer. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp 1\u201313","DOI":"10.1145\/3458817.3476161"},{"key":"5641_CR14","unstructured":"Thomas LH (1949) Elliptic problems in linear differential equations over a network"},{"issue":"24","key":"5641_CR15","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1002\/cpe.4909","volume":"30","author":"P Valero-Lara","year":"2018","unstructured":"Valero-Lara P, Mart\u00ednez-P\u00e9rez I, Sirvent R, Martorell X, Pena AJ (2018) cuthomasbatch and cuthomasvbatch, cuda routines to compute batch of tridiagonal systems on nvidia gpus. Concurr Comput Pract Exp 30(24):4909","journal-title":"Concurr Comput Pract Exp"},{"issue":"3","key":"5641_CR16","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1051\/meca\/2020013","volume":"21","author":"M Souri","year":"2020","unstructured":"Souri M, Akbarzadeh P, Darian HM (2020) Parallel thomas approach development for solving tridiagonal systems in gpu programming- steady and unsteady flow simulation. Mech Ind 21(3):303","journal-title":"Mech Ind"},{"key":"5641_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2021.113706","volume":"399","author":"JT Parker","year":"2022","unstructured":"Parker JT, Hill PA, Dickinson D, Dudson BD (2022) Parallel tridiagonal matrix inversion with a hybrid multigrid-thomas algorithm method. J Comput Appl Math 399:113706","journal-title":"J Comput Appl Math"},{"key":"5641_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2020.107722","volume":"260","author":"K-H Kim","year":"2021","unstructured":"Kim K-H, Kang J-H, Pan X, Choi J-I (2021) Pascal_tdma: a library of parallel and scalable solvers for massive tridiagonal systems. Comput Phys Commun 260:107722","journal-title":"Comput Phys Commun"},{"issue":"4","key":"5641_CR19","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1137\/0707049","volume":"7","author":"BL Buzbee","year":"1970","unstructured":"Buzbee BL, Golub GH, Nielson CW (1970) On direct methods for solving poisson\u2019s equations. SIAM J Numer Anal 7(4):627\u2013656","journal-title":"SIAM J Numer Anal"},{"issue":"1","key":"5641_CR20","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/321250.321259","volume":"12","author":"RW Hockney","year":"1965","unstructured":"Hockney RW (1965) A fast direct solution of Poisson\u2019s equation using Fourier analysis. J ACM 12(1):95\u2013113","journal-title":"J ACM"},{"issue":"1","key":"5641_CR21","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/321738.321741","volume":"20","author":"HS Stone","year":"1973","unstructured":"Stone HS (1973) An efficient parallel algorithm for the solution of a tridiagonal linear system of equations. J ACM 20(1):27\u201338","journal-title":"J ACM"},{"key":"5641_CR22","volume-title":"Parallel computers : architecture, programming, and algorithms","author":"RW Hockney","year":"1981","unstructured":"Hockney RW, Jesshope CR (1981) Parallel computers\u202f: architecture, programming, and algorithms. Adam Hilger"},{"issue":"2\u20133","key":"5641_CR23","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0167-8191(05)80104-8","volume":"17","author":"SM M\u00fcller","year":"1991","unstructured":"M\u00fcller SM, Scheerer D (1991) A method to parallelize tridiagonal solvers. Parallel Comput 17(2\u20133):181\u2013188","journal-title":"Parallel Comput"},{"key":"5641_CR24","doi-asserted-by":"crossref","unstructured":"Kim H.-S, Wu S, Chang L.-w, Wen-mei W.H (2011) A scalable tridiagonal solver for gpus. In: 2011 International Conference on Parallel Processing, pp 444\u2013453 . IEEE","DOI":"10.1109\/ICPP.2011.41"},{"key":"5641_CR25","doi-asserted-by":"crossref","unstructured":"Liu K, Wang X, Xue W (2022) Model guided algorithm optimization for tridiagonal solver on many-core architectures. CCF Transactions on High Performance Computing, 1\u201313","DOI":"10.1007\/s42514-022-00124-w"},{"key":"5641_CR26","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1016\/j.cam.2018.05.051","volume":"344","author":"S Li","year":"2018","unstructured":"Li S, Rouet F-H, Liu J, Huang C, Gao X, Chi X (2018) An efficient hybrid tridiagonal divide-and-conquer algorithm on distributed memory architectures. J Comput Appl Math 344:512\u2013520","journal-title":"J Comput Appl Math"},{"key":"5641_CR27","doi-asserted-by":"crossref","unstructured":"Chang L-W, Stratton JA, Kim H-S, Hwu W-MW (2012) A scalable, numerically stable, high-performance tridiagonal solver using gpus. In: SC\u201912: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, pp 1\u201311. IEEE","DOI":"10.1109\/SC.2012.12"},{"issue":"1","key":"5641_CR28","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TPDS.2019.2907537","volume":"32","author":"G Xiao","year":"2019","unstructured":"Xiao G, Li K, Chen Y, He W, Zomaya AY, Li T (2019) Caspmv: a customized and accelerative spmv framework for the sunway taihulight. IEEE Trans Parallel Distrib Syst 32(1):131\u2013146","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"2","key":"5641_CR29","doi-asserted-by":"publisher","first-page":"1020","DOI":"10.1109\/TETC.2018.2881265","volume":"9","author":"X Zhong","year":"2018","unstructured":"Zhong X, Li M, Yang H, Liu Y, Qian D (2018) swmr: a framework for accelerating mapreduce applications on sunway taihulight. IEEE Trans Emerg Topics Computi 9(2):1020\u20131030","journal-title":"IEEE Trans Emerg Topics Computi"},{"key":"5641_CR30","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1016\/j.future.2020.08.028","volume":"114","author":"Z Xiao","year":"2021","unstructured":"Xiao Z, Liu X, Xu J, Sun Q, Gan L (2021) Highly scalable parallel genetic algorithm on sunway many-core processors. Future Gener Comput Syst 114:679\u2013691","journal-title":"Future Gener Comput Syst"},{"key":"5641_CR31","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1007\/s42514-021-00072-x","volume":"3","author":"S Liu","year":"2021","unstructured":"Liu S, Gao J, Liu X, Huang Z, Zheng T (2021) Establishing high performance ai ecosystem on sunway platform. CCF Trans High Perform Comput 3:224\u2013241","journal-title":"CCF Trans High Perform Comput"},{"key":"5641_CR32","doi-asserted-by":"crossref","unstructured":"Shang H, Chen X, Gao X, Lin R, Wang L, Li F, Xiao Q, Xu L, Sun Q, Zhu L (2021) Tensorkmc: kinetic monte carlo simulation of 50 trillion atoms driven by deep learning on a new generation of sunway supercomputer","DOI":"10.1145\/3458817.3476174"},{"key":"5641_CR33","unstructured":"Zhu Q, Luo H, Yang C, Ding M, Yin W, Yuan X. Enabling and scaling the hpcg benchmark on the newest generation sunway supercomputer with 42 million heterogeneous cores. In: SC21: International Conference for High Performance Computing, Networking, Storage and Analysis"},{"issue":"9","key":"5641_CR34","doi-asserted-by":"publisher","first-page":"11441","DOI":"10.1007\/s11227-021-04270-w","volume":"78","author":"M Tian","year":"2022","unstructured":"Tian M, Wang J, Zhang Z, Du W, Pan J, Liu T (2022) swsuperlu: a highly scalable sparse direct solver on sunway manycore architecture. J Supercomput 78(9):11441\u201311463","journal-title":"J Supercomput"},{"key":"5641_CR35","doi-asserted-by":"crossref","unstructured":"Fang J, Fu H, Zhao W, Chen B, Yang G (2017) swdnn: a library for accelerating deep learning applications on sunway taihulight. IEEE","DOI":"10.1109\/IPDPS.2017.20"},{"key":"5641_CR36","doi-asserted-by":"crossref","unstructured":"Liu F, Ma W, Zhao Y, Chen D, Hu Y, Lu Q, Yin W, Yuan X, Jiang L, Yan H, et al (2022) xmath2. 0: a high-performance extended math library for sw26010-pro many-core processor. CCF Transactions on High Performance Computing, 1\u201316","DOI":"10.1007\/s42514-022-00130-y"},{"key":"5641_CR37","doi-asserted-by":"crossref","unstructured":"Wang X, Liu W, Wei X, Li W (2018) swsptrsv: a fast sparse triangular solve with sparse level tile layout on sunway architectures. In: the 23rd ACM SIGPLAN Symposium","DOI":"10.1145\/3178487.3178513"},{"key":"5641_CR38","doi-asserted-by":"publisher","unstructured":"Higham N.J. Accuracy and Stability of Numerical Algorithms, 2nd edn. Society for Industrial and Applied Mathematics. https:\/\/doi.org\/10.1137\/1.9780898718027","DOI":"10.1137\/1.9780898718027"},{"key":"5641_CR39","doi-asserted-by":"crossref","unstructured":"Ji J, Huang K, Suo X, Zhao J, Yan W (2022) Research on parallel algorithms for solving tridiagonal sparse linear equations. In: International Conference on Algorithms, Microchips and Network Applications, vol. 12176, pp. 192\u2013198 . SPIE","DOI":"10.1117\/12.2636414"},{"issue":"10","key":"5641_CR40","doi-asserted-by":"publisher","first-page":"1654","DOI":"10.3778\/j.issn.1673-9418.1811030","volume":"13","author":"L Kan","year":"2019","unstructured":"Kan L, Xinliang W, Ping XU, Wei X (2019) Parallel tridiagonal solver on sunway many-core processors. J Front Comput Sci Technol 13(10):1654\u20131663. https:\/\/doi.org\/10.3778\/j.issn.1673-9418.1811030","journal-title":"J Front Comput Sci Technol"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05641-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-023-05641-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05641-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T11:16:51Z","timestamp":1708168611000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-023-05641-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,19]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["5641"],"URL":"https:\/\/doi.org\/10.1007\/s11227-023-05641-1","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,19]]},"assertion":[{"value":"30 August 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that the authors have no competing interests as defined by Springer, or other interests that might be perceived to influence the results and\/or discussion reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"In this paper, the declaration is not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}