{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T22:36:28Z","timestamp":1769639788268,"version":"3.49.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Ministry of Economy and Competitiveness of Spain"},{"DOI":"10.13039\/501100002924","name":"FEDER Funds of the European Union","doi-asserted-by":"publisher","award":["TIN2013-42148-P"],"award-info":[{"award-number":["TIN2013-42148-P"]}],"id":[{"id":"10.13039\/501100002924","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002924","name":"FEDER Funds of the European Union","doi-asserted-by":"publisher","award":["TIN2016-75845-P"],"award-info":[{"award-number":["TIN2016-75845-P"]}],"id":[{"id":"10.13039\/501100002924","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Galician Government"},{"DOI":"10.13039\/501100002924","name":"FEDER funds of the EU under the Consolidation Program of Competitive Reference Groups","doi-asserted-by":"publisher","award":["GRC2013-055"],"award-info":[{"award-number":["GRC2013-055"]}],"id":[{"id":"10.13039\/501100002924","id-type":"DOI","asserted-by":"publisher"}]},{"name":"FPU Program"},{"name":"Ministry of Education of Spain","award":["FPU14\/02801"],"award-info":[{"award-number":["FPU14\/02801"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2018,1,1]]},"DOI":"10.1109\/tc.2017.2723879","type":"journal-article","created":{"date-parts":[[2017,7,6]],"date-time":"2017-07-06T18:09:23Z","timestamp":1499364563000},"page":"86-101","source":"Crossref","is-referenced-by-count":21,"title":["Solving Large Problem Sizes of Index-Digit Algorithms on GPU: FFT and Tridiagonal System Solvers"],"prefix":"10.1109","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7168-9050","authenticated-orcid":false,"given":"Adrian Perez","family":"Dieguez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Margarita","family":"Amor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacobo","family":"Lobeiras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramon","family":"Doallo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1464182.1464209"},{"key":"ref38","article-title":"Operator string algebraic properties and usage","author":"dieguez","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339596"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555254"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370858"},{"key":"ref30","author":"kirk","year":"2012","journal-title":"Programming Massively Parallel Processors A Hands-on Approach"},{"key":"ref37","article-title":"Use registers and multiple outputs per thread on GPU","author":"volkov","year":"2010","journal-title":"Proc Int Workshop Parallel Matrix Algorithms Appl"},{"key":"ref36","article-title":"Better performance at lower occupancy","author":"volkov","year":"2010","journal-title":"Proc GPU Technology Conf"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.12.003"},{"key":"ref34","year":"2015","journal-title":"CUB Library"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693472"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SPDP.1991.218237"},{"key":"ref11","first-page":"4:1","article-title":"Register packing for cyclic reduction: A case study","author":"davison","year":"2011","journal-title":"Proc 4th Workshop General Purpose Process Graph Process Units"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.92"},{"key":"ref13","author":"hockney","year":"1988","journal-title":"Parallel Computers 2 Architecture Programming and Algorithms"},{"key":"ref14","article-title":"Elliptic problems in linear difference equations over a network","author":"thomas","year":"1949"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.03.003"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/321250.321259"},{"key":"ref17","article-title":"Mapping tridiagonal solvers to linear recurrences","author":"chang","year":"2013"},{"key":"ref18","first-page":"444","article-title":"A scalable tridiagonal solver for GPU","author":"kim","year":"2011","journal-title":"Proc Int Conf Parallel Process"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/322047.322054"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(95)00062-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654090"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2450718"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1941553.1941589"},{"key":"ref6","first-page":"34:1","article-title":"Tera-scale 1D FFT with low-communication algorithm and Intel® Xeon Phi™ coprocessors","author":"park","year":"2013","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-014-0323-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.100"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.95"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CSE.2013.36"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/322217.322232"},{"key":"ref9","volume":"5 0","year":"2012","journal-title":"NVIDIA CUDA CUFFT Library"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/321941.321949"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.12"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-014-1299-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2015.03.008"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"31:1","DOI":"10.1145\/2830568","article-title":"Manycore algorithms for batch scalar and block tridiagonal solvers","volume":"42","author":"l\u00e1szl\u00f3","year":"2016","journal-title":"ACM Trans Math Softw"},{"key":"ref41","article-title":"Design and evaluation of tridiagonal solvers for vector and parallel computers","author":"pey","year":"1995"},{"key":"ref23","volume":"5 0","year":"2012","journal-title":"CUSPARSE Library"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2516988"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.83"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/8176066\/07970194.pdf?arnumber=7970194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:23:36Z","timestamp":1642004616000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7970194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1,1]]},"references-count":41,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tc.2017.2723879","relation":{},"ISSN":["0018-9340"],"issn-type":[{"value":"0018-9340","type":"print"}],"subject":[],"published":{"date-parts":[[2018,1,1]]}}}