{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T22:06:21Z","timestamp":1773525981710,"version":"3.50.1"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,11,2]],"date-time":"2018-11-02T00:00:00Z","timestamp":1541116800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"publisher","award":["TIN2016-75845-P"],"award-info":[{"award-number":["TIN2016-75845-P"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010801","name":"Xunta de Galicia","doi-asserted-by":"crossref","award":["GRC2013-055"],"award-info":[{"award-number":["GRC2013-055"]}],"id":[{"id":"10.13039\/501100010801","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010568","name":"Secretaria Xeral de Investigaci\u00f3n e Desenvolvemento, Xunta de Galicia","doi-asserted-by":"publisher","award":["Ref. R2014\/049"],"award-info":[{"award-number":["Ref. R2014\/049"]}],"id":[{"id":"10.13039\/501100010568","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010568","name":"Secretaria Xeral de Investigaci\u00f3n e Desenvolvemento, Xunta de Galicia","doi-asserted-by":"publisher","award":["Ref. R2016\/037"],"award-info":[{"award-number":["Ref. R2016\/037"]}],"id":[{"id":"10.13039\/501100010568","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003176","name":"Ministerio de Educaci\u00f3n, Cultura y Deporte","doi-asserted-by":"crossref","award":["FPU14\/02801"],"award-info":[{"award-number":["FPU14\/02801"]}],"id":[{"id":"10.13039\/501100003176","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s11227-018-2676-z","type":"journal-article","created":{"date-parts":[[2018,11,2]],"date-time":"2018-11-02T02:08:47Z","timestamp":1541124527000},"page":"1510-1523","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Parallel prefix operations on GPU: tridiagonal system solvers and scan operators"],"prefix":"10.1007","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7168-9050","authenticated-orcid":false,"given":"Adri\u00e1n P.","family":"Di\u00e9guez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Margarita","family":"Amor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ram\u00f3n","family":"Doallo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,2]]},"reference":[{"key":"2676_CR1","doi-asserted-by":"crossref","unstructured":"Davidson A, Zhang Y, Owens JD (2011) An auto-tuned method for solving large tridiagonal systems on the GPU. In: Proceedings of the 25th IEEE International Parallel and Distributed Processing Symposium (IPDPS\u201911), pp 956\u2013965","DOI":"10.1109\/IPDPS.2011.92"},{"issue":"3","key":"2676_CR2","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1109\/TC.1982.1675982","volume":"31","author":"RP Brent","year":"1982","unstructured":"Brent RP, Kung H (1982) A regular layout for parallel adders. IEEE Trans Comput 31(3):260\u2013264. \n                    https:\/\/doi.org\/10.1109\/TC.1982.1675982","journal-title":"IEEE Trans Comput"},{"key":"2676_CR3","doi-asserted-by":"crossref","unstructured":"Chang LW, Stratton JA, Kim HS, Hwu WMW (2012) A scalable, numerically stable, high-performance tridiagonal solver using GPUs. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC\u201912), pp 27:1\u201327:11","DOI":"10.1109\/SC.2012.12"},{"key":"2676_CR4","doi-asserted-by":"crossref","unstructured":"Davidson A, Owens JD (2011) Register packing for cyclic reduction. In: Proceedings of the 4th Workshop on General Purpose Processing on Graphics Processing Units GPGPU-4, pp 4:1\u20134:6","DOI":"10.1145\/1964179.1964185"},{"key":"2676_CR5","doi-asserted-by":"crossref","unstructured":"Di\u00e9guez AP, Amor M, Doallo R (2015) New tridiagonal systems solvers on GPU architectures. In: Proceedings of IEEE International Conference on High Performance Computing (HiPC\u201915), pp 85\u201393","DOI":"10.1109\/HiPC.2015.17"},{"key":"2676_CR6","unstructured":"Di\u00e9guez AP, Amor M, Doallo R (2018) A tuning strategy for tridiagonal system solvers on GPU. In: Proceedings of the 18th International Conference on Computational and Mathematical Methods in Science and Engineering, CMMSE\u201918"},{"issue":"1","key":"2676_CR7","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TC.2017.2723879","volume":"67","author":"AP Di\u00e9guez","year":"2018","unstructured":"Di\u00e9guez AP, Amor M, Lobeiras J, Doallo R (2018) Solving large problem sizes of index-digit algorithms on GPU: FFT and tridiagonal system solvers. IEEE Trans Comput 67(1):86\u2013101. \n                    https:\/\/doi.org\/10.1109\/TC.2017.2723879","journal-title":"IEEE Trans Comput"},{"key":"2676_CR8","doi-asserted-by":"crossref","unstructured":"Dotsenko Y, Govindaraju NK, Sloan PP, Boyd C, Manferdelli J (2008) Fast scan algorithms on graphics processors. In: Proceedings of the 22nd Annual International Conference on Supercomputing, pp 205\u2013213","DOI":"10.1145\/1375527.1375559"},{"key":"2676_CR9","unstructured":"Harris M, Sengupta S, Owens JD (2007) Parallel prefix sum (scan) with CUDA. In: GPU Gems 3. Addison Wesley"},{"key":"2676_CR10","volume-title":"Parallel computers 2: architecture, programming and algorithms","author":"R Hockney","year":"1988","unstructured":"Hockney R, Jesshope C (1988) Parallel computers 2: architecture, programming and algorithms. Taylor & Francis, Milton Park"},{"issue":"1","key":"2676_CR11","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"},{"key":"2676_CR12","doi-asserted-by":"publisher","unstructured":"Kim H, Wu S, Chang L, Hwu WW (2011) A scalable tridiagonal solver for GPUs. In: Proceedings of the International Conference on Parallel Processing (ICPP\u201911), pp 444\u2013453. \n                    https:\/\/doi.org\/10.1109\/ICPP.2011.41","DOI":"10.1109\/ICPP.2011.41"},{"issue":"8","key":"2676_CR13","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1109\/TC.1973.5009159","volume":"22","author":"PM Kogge","year":"1973","unstructured":"Kogge PM, Stone HS (1973) A parallel algorithm for the efficient solution of a general class of recurrence equations. IEEE Trans Comput 22(8):786\u2013793","journal-title":"IEEE Trans Comput"},{"issue":"4","key":"2676_CR14","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1145\/322217.322232","volume":"27","author":"RE Ladner","year":"1980","unstructured":"Ladner RE, Fischer MJ (1980) Parallel prefix computation. J ACM 27(4):831\u2013838. \n                    https:\/\/doi.org\/10.1145\/322217.322232","journal-title":"J ACM"},{"issue":"4","key":"2676_CR15","doi-asserted-by":"publisher","first-page":"31:1","DOI":"10.1145\/2830568","volume":"42","author":"E L\u00e1szl\u00f3","year":"2016","unstructured":"L\u00e1szl\u00f3 E, Giles M, Appleyard J (2016) Manycore algorithms for batch scalar and block tridiagonal solvers. ACM Trans Math Softw 42(4):31:1\u201331:36","journal-title":"ACM Trans Math Softw"},{"issue":"6","key":"2676_CR16","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.1007\/s10766-014-0323-8","volume":"43","author":"J Lobeiras","year":"2015","unstructured":"Lobeiras J, Amor M, Doallo R (2015) BPLG: a tuned butterfly processing library for GPU architectures. Int J Parallel Program 43(6):1078\u20131102","journal-title":"Int J Parallel Program"},{"issue":"5","key":"2676_CR17","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1109\/TPDS.2015.2450718","volume":"27","author":"J Lobeiras","year":"2016","unstructured":"Lobeiras J, Amor M, Doallo R (2016) Designing efficient index-digit algorithms for CUDA GPU architectures. IEEE Trans Parallel Distrib Syst 27(5):1331\u20131343","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"2676_CR18","unstructured":"NVIDIA-Corporation (2012) CUDA CUSPARSE library"},{"key":"2676_CR19","unstructured":"NVIDIA-Corporation (2013) Modern GPU library. \n                    https:\/\/github.com\/NVlabs\/moderngpu\n                    \n                  . Accessed 01 Nov 2018"},{"key":"2676_CR20","unstructured":"NVIDIA-Corporation (2014) CUDPP: CUDA data parallel primitives library. \n                    http:\/\/cudpp.github.io\/\n                    \n                  . Accessed 01 Nov 2018"},{"key":"2676_CR21","unstructured":"NVIDIA-Corporation (2015a) CUB library. \n                    http:\/\/nvlabs.github.io\/cub\/\n                    \n                  . Accessed 01 Nov 2018"},{"key":"2676_CR22","unstructured":"NVIDIA-Corporation (2015b) Thrust library. \n                    https:\/\/github.com\/thrust\/thrust\n                    \n                  . Accessed 01 Nov 2018"},{"key":"2676_CR23","unstructured":"Sengupta S, Harris M, Garland M (2008) Efficient parallel scan algorithms for GPUs. Technical report"},{"key":"2676_CR24","unstructured":"Sengupta S, Lefohn AE, Owens JD (2006) A work-efficient step-efficient prefix sum algorithm. Workshop on edge computing using new commodity architectures"},{"issue":"8","key":"2676_CR25","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1145\/2517327.2442539","volume":"48","author":"S Yan","year":"2013","unstructured":"Yan S, Long G, Zhang Y (2013) Streamscan: fast scan algorithms for gpus without global barrier synchronization. SIGPLAN Not 48(8):229\u2013238","journal-title":"SIGPLAN Not"},{"issue":"5","key":"2676_CR26","doi-asserted-by":"publisher","first-page":"1760","DOI":"10.1007\/s11227-016-1881-x","volume":"73","author":"W Yang","year":"2017","unstructured":"Yang W, Li K, Li K (2017) A parallel solving method for block-tridiagonal equations on CPU\u2013GPU heterogeneous computing systems. J Supercomput 73(5):1760\u20131781","journal-title":"J Supercomput"},{"key":"2676_CR27","doi-asserted-by":"crossref","unstructured":"Zhang Y, Cohen J, Owens JD (2010) Fast tridiagonal solvers on the GPU. In: Proceeding of the 15th ACM Symposium on Principles and Practice of Parallel Programming (PPoPP\u201910), pp 127\u2013136","DOI":"10.1145\/1693453.1693472"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2676-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-018-2676-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2676-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T20:23:57Z","timestamp":1572639837000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-018-2676-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,2]]},"references-count":27,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["2676"],"URL":"https:\/\/doi.org\/10.1007\/s11227-018-2676-z","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,2]]},"assertion":[{"value":"2 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}