{"id":"https://openalex.org/W2731702594","doi":"https://doi.org/10.1109/tc.2017.2723879","title":"Solving Large Problem Sizes of Index-Digit Algorithms on GPU: FFT and Tridiagonal System Solvers","display_name":"Solving Large Problem Sizes of Index-Digit Algorithms on GPU: FFT and Tridiagonal System Solvers","publication_year":2017,"publication_date":"2017-07-06","ids":{"openalex":"https://openalex.org/W2731702594","doi":"https://doi.org/10.1109/tc.2017.2723879","mag":"2731702594"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2017.2723879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2017.2723879","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049023670","display_name":"Adri\u00e1n Perez Di\u00e9guez","orcid":"https://orcid.org/0000-0001-7168-9050"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adrian Perez Dieguez","raw_affiliation_strings":["Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"raw_orcid":"https://orcid.org/0000-0001-7168-9050","affiliations":[{"raw_affiliation_string":"Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068836759","display_name":"Margarita Amor","orcid":"https://orcid.org/0000-0003-4641-7891"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Margarita Amor","raw_affiliation_strings":["Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060934969","display_name":"Jacobo Lobeiras","orcid":null},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jacobo Lobeiras","raw_affiliation_strings":["Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070686724","display_name":"Ram\u00f3n Doallo","orcid":"https://orcid.org/0000-0002-6011-3387"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ramon Doallo","raw_affiliation_strings":["Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I11019714"],"apc_list":null,"apc_paid":null,"fwci":2.0126,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88023592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"67","issue":"1","first_page":"86","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11321","display_name":"Error Correcting Code Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.831439733505249},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7221094369888306},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.6709265112876892},{"id":"https://openalex.org/keywords/tridiagonal-matrix","display_name":"Tridiagonal matrix","score":0.5838291049003601},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5631597638130188},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.55619877576828},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4983394145965576},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.4715571403503418},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.44396671652793884},{"id":"https://openalex.org/keywords/twiddle-factor","display_name":"Twiddle factor","score":0.41551434993743896},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3646796941757202},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.15282312035560608},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11809226870536804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.831439733505249},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7221094369888306},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.6709265112876892},{"id":"https://openalex.org/C51647924","wikidata":"https://www.wikidata.org/wiki/Q1755277","display_name":"Tridiagonal matrix","level":3,"score":0.5838291049003601},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5631597638130188},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.55619877576828},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4983394145965576},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4715571403503418},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.44396671652793884},{"id":"https://openalex.org/C4697666","wikidata":"https://www.wikidata.org/wiki/Q7857913","display_name":"Twiddle factor","level":5,"score":0.41551434993743896},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3646796941757202},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.15282312035560608},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11809226870536804},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tc.2017.2723879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2017.2723879","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},{"id":"pmh:oai:ruc.udc.es:2183/20961","is_oa":false,"landing_page_url":"http://hdl.handle.net/2183/20961","pdf_url":null,"source":{"id":"https://openalex.org/S4306402204","display_name":"RUC (Universidade Da Coru\u00f1a)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G1322333988","display_name":null,"funder_award_id":"TIN2016-75845-P","funder_id":"https://openalex.org/F4320321595","funder_display_name":"Federaci\u00f3n Espa\u00f1ola de Enfermedades Raras"},{"id":"https://openalex.org/G494760652","display_name":null,"funder_award_id":"TIN2013-42148-P","funder_id":"https://openalex.org/F4320321595","funder_display_name":"Federaci\u00f3n Espa\u00f1ola de Enfermedades Raras"},{"id":"https://openalex.org/G8764979820","display_name":null,"funder_award_id":"GRC2013-055","funder_id":"https://openalex.org/F4320321595","funder_display_name":"Federaci\u00f3n Espa\u00f1ola de Enfermedades Raras"}],"funders":[{"id":"https://openalex.org/F4320321595","display_name":"Federaci\u00f3n Espa\u00f1ola de Enfermedades Raras","ror":"https://ror.org/0348bpk17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1480666649","https://openalex.org/W1512833653","https://openalex.org/W1629601946","https://openalex.org/W1762731526","https://openalex.org/W1979359863","https://openalex.org/W1990523337","https://openalex.org/W1997659541","https://openalex.org/W2008110907","https://openalex.org/W2013855928","https://openalex.org/W2022552329","https://openalex.org/W2035975621","https://openalex.org/W2045992017","https://openalex.org/W2047610878","https://openalex.org/W2048332769","https://openalex.org/W2089309544","https://openalex.org/W2094677173","https://openalex.org/W2102512593","https://openalex.org/W2107483876","https://openalex.org/W2111946172","https://openalex.org/W2112185810","https://openalex.org/W2119640849","https://openalex.org/W2123440268","https://openalex.org/W2130749431","https://openalex.org/W2134427337","https://openalex.org/W2141524575","https://openalex.org/W2143462372","https://openalex.org/W2158261096","https://openalex.org/W2160406723","https://openalex.org/W2161456019","https://openalex.org/W2323164726","https://openalex.org/W2345127431","https://openalex.org/W2461005004","https://openalex.org/W2480005405","https://openalex.org/W2485003951","https://openalex.org/W4210691403","https://openalex.org/W4239609053","https://openalex.org/W4384823179","https://openalex.org/W6630833644"],"related_works":["https://openalex.org/W2110451206","https://openalex.org/W2080076943","https://openalex.org/W2025911710","https://openalex.org/W2364044215","https://openalex.org/W189420351","https://openalex.org/W2167848747","https://openalex.org/W2009169896","https://openalex.org/W2806238950","https://openalex.org/W2191246539","https://openalex.org/W2966890395"],"abstract_inverted_index":{"Current":[0],"Graphics":[1],"Processing":[2],"Units":[3],"(GPUs)":[4],"are":[5,43,62],"capable":[6],"of":[7,57,70,108,111,114,116,172],"obtaining":[8],"high":[9],"computational":[10],"performance":[11],"in":[12,33,36,53,186],"scientific":[13],"applications.":[14],"Nevertheless,":[15],"programmers":[16],"have":[17,28],"to":[18,29,38,105,132,174,178,184],"use":[19],"suitable":[20],"parallel":[21,97],"algorithms":[22,72,99,137],"for":[23,47,73,95,138,191],"these":[24],"architectures":[25],"and":[26,146,160,164,182],"usually":[27],"consider":[30],"optimization":[31],"techniques":[32],"the":[34,54,68,112,139,153],"implementation":[35,157],"order":[37],"achieve":[39],"said":[40],"performance.":[41],"There":[42],"many":[44],"efficient":[45,71],"proposals":[46,65],"limited-size":[48],"problems":[49],"which":[50],"fit":[51],"directly":[52],"shared":[55,79],"memory":[56,80],"CUDA":[58],"GPUs,":[59],"however,":[60],"there":[61],"few":[63],"GPU":[64],"that":[66,77,91,100],"tackle":[67],"design":[69],"large":[74],"problem":[75,94],"sizes":[76],"exceed":[78],"storage":[81],"capacity.":[82],"In":[83],"this":[84,93],"work,":[85],"we":[86],"present":[87],"a":[88,106,147],"tuning":[89],"strategy":[90,128],"addresses":[92],"some":[96],"prefix":[98],"can":[101],"be":[102],"represented":[103],"according":[104],"set":[107],"common":[109],"permutations":[110],"digits":[113],"each":[115],"its":[117],"element":[118],"indices":[119],"[1],":[120],"denoted":[121],"as":[122],"Index-Digit":[123],"(ID)":[124],"algorithms.":[125],"Specifically,":[126],"our":[127],"has":[129],"been":[130],"applied":[131],"develop":[133],"flexible":[134],"Multi-Stage":[135],"(MS)":[136],"Fast":[140],"Fourier":[141],"Transform":[142],"(FFT)":[143],"algorithm":[144],"(MS-ID-FFT)":[145],"tridiagonal":[148,194],"system":[149],"solver":[150],"(MS-ID-TS)":[151],"on":[152],"GPU.":[154],"The":[155],"resulting":[156],"is":[158],"compact":[159],"outperforms":[161],"other":[162],"well-known":[163],"commonly":[165],"used":[166],"state-of-the-art":[167],"libraries,":[168],"with":[169,176,188],"an":[170],"improvement":[171],"up":[173,183],"1.47x":[175],"respect":[177],"NVIDIA's":[179,189],"complex":[180],"CUFFT,":[181],"33.2x":[185],"comparison":[187],"CUSPARSE":[190],"real":[192],"data":[193],"systems.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6}],"updated_date":"2026-07-07T14:30:12.667765","created_date":"2025-10-10T00:00:00"}
