{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:42:19Z","timestamp":1740181339893,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T00:00:00Z","timestamp":1664409600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T00:00:00Z","timestamp":1664409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2020YFA0607903"],"award-info":[{"award-number":["2020YFA0607903"]}],"id":[{"id":"10.13039\/501100012166","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":[[2023,3]]},"DOI":"10.1007\/s42514-022-00124-w","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T12:02:32Z","timestamp":1664452952000},"page":"43-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Model guided algorithm optimization for tridiagonal solver on many-core architectures"],"prefix":"10.1007","volume":"5","author":[{"given":"Kan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinliang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9740-6581","authenticated-orcid":false,"given":"Wei","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,29]]},"reference":[{"key":"124_CR1","doi-asserted-by":"crossref","unstructured":"Chang, L.W., Lo, M.T., Anssari, N., Hsu, K.H., Huang, N.E., Hwu, W.M.: Parallel implementation of multi-dimensional ensemble empirical mode decomposition. In: Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, IEEE, pp. 1621\u20131624 (2011)","DOI":"10.1109\/ICASSP.2011.5946808"},{"key":"124_CR2","doi-asserted-by":"crossref","unstructured":"Chang, L.W., Stratton, J.A., Kim, H.S., Hwu, W.M.W.: A scalable, numerically stable, high-performance tridiagonal solver using GPUS. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, IEEE Computer Society Press, p. 27 (2012)","DOI":"10.1109\/SC.2012.12"},{"key":"124_CR3","doi-asserted-by":"publisher","unstructured":"Davidson, A., Owens, J.D. Register packing for cyclic reduction: a case study. In: Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units, ACM, New York, NY, USA, GPGPU-4, pp. 4:1\u20134:6 (2011). https:\/\/doi.org\/10.1145\/1964179.1964185","DOI":"10.1145\/1964179.1964185"},{"key":"124_CR4","doi-asserted-by":"publisher","unstructured":"Davidson, A., Zhang, Y., Owens, J.D.: An auto-tuned method for solving large tridiagonal systems on the GPU. In: 2011 IEEE International Parallel Distributed Processing Symposium, pp. 956\u2013965 (2011). https:\/\/doi.org\/10.1109\/IPDPS.2011.92","DOI":"10.1109\/IPDPS.2011.92"},{"key":"124_CR5","doi-asserted-by":"publisher","unstructured":"Dieguez, A.P., Amor, M., Doallo, R.: New tridiagonal systems solvers on GPU architectures. In: 2015 IEEE 22nd International Conference on High Performance Computing (HiPC), pp. 85\u201394 (2015). https:\/\/doi.org\/10.1109\/HiPC.2015.17","DOI":"10.1109\/HiPC.2015.17"},{"issue":"1","key":"124_CR6","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TC.2017.2723879","volume":"67","author":"AP Dieguez","year":"2018","unstructured":"Dieguez, A.P., Amor, M., Lobeiras, J., Doallo, R.: Solving large problem sizes of index-digit algorithms on GPU: FFT and tridiagonal system solvers. IEEE Trans. Comput. 67(1), 86\u2013101 (2018). https:\/\/doi.org\/10.1109\/TC.2017.2723879","journal-title":"IEEE Trans. Comput."},{"issue":"1\u20132","key":"124_CR7","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/0377-0427(89)90362-2","volume":"27","author":"O Egecioglu","year":"1989","unstructured":"Egecioglu, O., Koc, C.K., Laub, A.J.: A recursive doubling algorithm for solution of tridiagonal systems on hypercube multiprocessors. J. Comput. Appl. Math. 27(1\u20132), 95\u2013108 (1989). https:\/\/doi.org\/10.1016\/0377-0427(89)90362-2. (reprinted in it Parallel algorithms for numerical linear algebra, 95-108, North-Holland, Amsterdam, 1990)","journal-title":"J. Comput. Appl. Math."},{"issue":"1","key":"124_CR8","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/TPDS.2010.61","volume":"22","author":"D Goddeke","year":"2011","unstructured":"Goddeke, D., Strzodka, R.: Cyclic reduction tridiagonal solvers on GPUS applied to mixed-precision multigrid. IEEE Trans. Parallel Distrib. Syst. 22(1), 22\u201332 (2011). https:\/\/doi.org\/10.1109\/TPDS.2010.61","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"124_CR9","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970937","volume-title":"Iterative Methods for Solving Linear Systems","author":"A Greenbaum","year":"1997","unstructured":"Greenbaum, A.: Iterative Methods for Solving Linear Systems, vol. 17. SIAM, Philadelphia (1997)"},{"key":"124_CR10","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/j.ocemod.2003.10.002","volume":"7","author":"GR Halliwell","year":"2004","unstructured":"Halliwell, G.R.: Evaluation of vertical coordinate and vertical mixing algorithms in the HYbrid-Coordinate Ocean Model (HYCOM). Ocean Model. 7, 285\u2013322 (2004). https:\/\/doi.org\/10.1016\/j.ocemod.2003.10.002","journal-title":"Ocean Model."},{"issue":"1","key":"124_CR11","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/321250.321259","volume":"12","author":"RW Hockney","year":"1965","unstructured":"Hockney, R.W.: A fast direct solution of Poisson\u2019s equation using Fourier analysis. J. ACM (JACM) 12(1), 95\u2013113 (1965)","journal-title":"J. ACM (JACM)"},{"key":"124_CR12","volume-title":"Parallel Computers Two: Architecture, Programming and Algorithms","author":"RW Hockney","year":"1988","unstructured":"Hockney, R.W., Jesshope, C.R.: Parallel Computers Two: Architecture, Programming and Algorithms, 2nd edn. IOP Publishing Ltd., Bristol (1988)","edition":"2"},{"key":"124_CR13","unstructured":"Kass, M., Lefohn, A., Owens, J.: Interactive depth of field using simulated diffusion on a GPU. Pixar Animation Studios Tech Report 2, 1\u20138 (2006)"},{"issue":"4","key":"124_CR14","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/97880.97884","volume":"24","author":"M Kass","year":"1990","unstructured":"Kass, M., Miller, G.: Rapid, stable fluid dynamics for computer graphics. SIGGRAPH Comput. Graph. 24(4), 49\u201357 (1990). https:\/\/doi.org\/10.1145\/97880.97884","journal-title":"SIGGRAPH Comput. Graph."},{"key":"124_CR15","doi-asserted-by":"publisher","unstructured":"Kim, H., Wu, S., Chang, L., Hwu, W.W.: A scalable tridiagonal solver for GPUS. In: 2011 International Conference on Parallel Processing, pp. 444\u2013453 (2011). https:\/\/doi.org\/10.1109\/ICPP.2011.41","DOI":"10.1109\/ICPP.2011.41"},{"key":"124_CR16","doi-asserted-by":"publisher","unstructured":"Lelbach, B.A., Johansen, H., Williams, S.: Simultaneously solving swarms of small sparse systems on SIMD silicon. In: 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 1128\u20131137 (2017). https:\/\/doi.org\/10.1109\/IPDPSW.2017.114","DOI":"10.1109\/IPDPSW.2017.114"},{"key":"124_CR17","unstructured":"McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. In: IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter, pp. 19\u201325 (1995)"},{"key":"124_CR18","doi-asserted-by":"publisher","unstructured":"Muller, S.M.: A method to parallelize tridiagonal solvers. Proceedings of the Fifth Distributed Memory Computing Conference 1990, 340\u2013345 (1990). https:\/\/doi.org\/10.1109\/DMCC.1990.555403","DOI":"10.1109\/DMCC.1990.555403"},{"issue":"2","key":"124_CR19","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.parco.2005.07.005","volume":"32","author":"E Polizzi","year":"2006","unstructured":"Polizzi, E., Sameh, A.H.: A parallel hybrid banded system solver: the spike algorithm. Parallel Comput. 32(2), 177\u2013194 (2006). https:\/\/doi.org\/10.1016\/j.parco.2005.07.005","journal-title":"Parallel Comput."},{"key":"124_CR20","unstructured":"Sakharnykh, N.: Tridiagonal solvers on the GPU and applications to fluid simulation. In: NVIDIA GPU Technology Conference (2009)"},{"key":"124_CR21","unstructured":"Sakharnykh, N.: Efficient tridiagonal solvers for ADI methods and fluid simulation. In: NVIDIA GPU Technology Conference (2010)"},{"key":"124_CR22","unstructured":"Sengupta, S., Harris, M., Zhang, Y., Owens, J.D.: Scan primitives for gpu computing. In: Proceedings of the 22nd ACM SIGGRAPH\/EUROGRAPHICS Symposium on Graphics Hardware, Eurographics Association, Aire-la-Ville, Switzerland, Switzerland, GH \u201907, pp. 97\u2013106 (2007)"},{"issue":"1","key":"124_CR23","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/321738.321741","volume":"20","author":"HS Stone","year":"1973","unstructured":"Stone, H.S.: An efficient parallel algorithm for the solution of a tridiagonal linear system of equations. J. ACM (JACM) 20(1), 27\u201338 (1973)","journal-title":"J. ACM (JACM)"},{"key":"124_CR24","volume-title":"Elliptic Problems in Linear Difference Equations Over a Network","author":"LH Thomas","year":"1949","unstructured":"Thomas, L.H.: Elliptic Problems in Linear Difference Equations Over a Network. Columbia University, New York, Watson Sci Comput Lab Rept (1949)"},{"key":"124_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., Xu, Y., Xue, W.: A hierarchical tridiagonal system solver for heterogenous supercomputers. In: Proceedings of the 5th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, pp. 69\u201376. IEEE Press (2014)","DOI":"10.1109\/ScalA.2014.12"},{"key":"124_CR26","doi-asserted-by":"publisher","unstructured":"Wang, X., Xue, W., Zhai, J., Xu, Y., Zheng, W., Lin, H.: A fast tridiagonal solver for intel mic architecture. In: 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 172\u2013181 (2016). https:\/\/doi.org\/10.1109\/IPDPS.2016.83","DOI":"10.1109\/IPDPS.2016.83"},{"issue":"2","key":"124_CR27","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1145\/355945.355947","volume":"7","author":"HH Wang","year":"1981","unstructured":"Wang, H.H.: A parallel method for tridiagonal equations. ACM Trans. Math. Softw. 7(2), 170\u2013183 (1981). https:\/\/doi.org\/10.1145\/355945.355947","journal-title":"ACM Trans. Math. Softw."},{"issue":"4","key":"124_CR28","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009). https:\/\/doi.org\/10.1145\/1498765.1498785","journal-title":"Commun. ACM"},{"key":"124_CR29","doi-asserted-by":"publisher","unstructured":"Xu, Z., Lin, J., Matsuoka, S.: Benchmarking sw26010 many-core processor. In: 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 743\u2013752 (2017). https:\/\/doi.org\/10.1109\/IPDPSW.2017.9","DOI":"10.1109\/IPDPSW.2017.9"},{"key":"124_CR30","doi-asserted-by":"publisher","unstructured":"Xu, S., Xu, Y., Xue, W., Shen, X., Zheng, F., Huang, X., Yang, G.: Taming the \u201cmonster\u201d: overcoming program optimization challenges on sw26010 through precise performance modeling. In: 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp 763\u2013773 (2018). https:\/\/doi.org\/10.1109\/IPDPS.2018.00086","DOI":"10.1109\/IPDPS.2018.00086"},{"issue":"5","key":"124_CR31","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1145\/1837853.1693472","volume":"45","author":"Y Zhang","year":"2010","unstructured":"Zhang, Y., Cohen, J., Owens, J.D.: Fast tridiagonal solvers on the GPU. SIGPLAN Not. 45(5), 127\u2013136 (2010). https:\/\/doi.org\/10.1145\/1837853.1693472","journal-title":"SIGPLAN Not."}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-022-00124-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-022-00124-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-022-00124-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,26]],"date-time":"2023-03-26T21:39:12Z","timestamp":1679866752000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-022-00124-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,29]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["124"],"URL":"https:\/\/doi.org\/10.1007\/s42514-022-00124-w","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"type":"print","value":"2524-4922"},{"type":"electronic","value":"2524-4930"}],"subject":[],"published":{"date-parts":[[2022,9,29]]},"assertion":[{"value":"7 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"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"}}]}}