{"id":"https://openalex.org/W2107483876","doi":"https://doi.org/10.1145/1654059.1654090","title":"Auto-tuning 3-D FFT library for CUDA GPUs","display_name":"Auto-tuning 3-D FFT library for CUDA GPUs","publication_year":2009,"publication_date":"2009-11-14","ids":{"openalex":"https://openalex.org/W2107483876","doi":"https://doi.org/10.1145/1654059.1654090","mag":"2107483876"},"language":"en","primary_location":{"id":"doi:10.1145/1654059.1654090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5006972521","display_name":"Akira Nukada","orcid":"https://orcid.org/0000-0001-7959-6975"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Nukada","raw_affiliation_strings":["Tokyo Institute of Technology and Japan Science and Technology Agency, CREST","Tokyo Institute of Technology, and Japan Science and Technology Agency, CREST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology and Japan Science and Technology Agency, CREST","institution_ids":["https://openalex.org/I4210086780","https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of Technology, and Japan Science and Technology Agency, CREST","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103252086","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-2126-2926"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["Tokyo Institute of Technology and National Institute of Informatics and Japan Science and Technology Agency, CREST","Tokyo Institute of Technology and National Institute of Informatics and Japan Science and Technology Agency, CREST#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology and National Institute of Informatics and Japan Science and Technology Agency, CREST","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I4210086780"]},{"raw_affiliation_string":"Tokyo Institute of Technology and National Institute of Informatics and Japan Science and Technology Agency, CREST#TAB#","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":137,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/cuda","display_name":"CUDA","score":0.8718912601470947},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.8377736806869507},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8330196142196655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8158535957336426},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5797469019889832},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5680879950523376},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.46358630061149597},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4207102358341217},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41638872027397156},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.35246729850769043},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24428746104240417},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.12241944670677185},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.09513455629348755},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06357795000076294}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8718912601470947},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8377736806869507},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8330196142196655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158535957336426},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5797469019889832},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5680879950523376},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.46358630061149597},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4207102358341217},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41638872027397156},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35246729850769043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24428746104240417},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.12241944670677185},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.09513455629348755},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06357795000076294},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1654059.1654090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1964031104","https://openalex.org/W2016677154","https://openalex.org/W2061171222","https://openalex.org/W2063186542","https://openalex.org/W2102182691","https://openalex.org/W2108600626","https://openalex.org/W2108792719","https://openalex.org/W2113904767","https://openalex.org/W2114927422","https://openalex.org/W2127091535","https://openalex.org/W2134572726","https://openalex.org/W2136952590","https://openalex.org/W2154786353","https://openalex.org/W2323594350","https://openalex.org/W2728600909","https://openalex.org/W6654554885"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Existing":[0],"implementations":[1,129],"of":[2,14,49,99,142],"FFTs":[3,48],"on":[4,40,61,108,130],"GPUs":[5,62],"are":[6,111],"optimized":[7],"for":[8,47,63],"specific":[9],"transform":[10,51],"sizes":[11,30,144],"like":[12],"powers":[13],"two,":[15],"and":[16,19,69,84,101,119,136],"exhibit":[17],"unstable":[18],"peaky":[20],"performance":[21,44,122,140],"i.e.,":[22],"do":[23],"not":[24],"perform":[25],"as":[26,67,88,95],"well":[27],"in":[28,33,121],"other":[29],"that":[31,76,123],"appear":[32],"practice.":[34],"Our":[35,114],"new":[36],"auto-tuning":[37,57],"3-D":[38,89,127],"FFT":[39,128],"CUDA":[41,45],"generates":[42],"high":[43],"kernels":[46,65,86],"varying":[50],"sizes,":[52],"alleviating":[53],"this":[54,71],"problem.":[55],"Although":[56],"has":[58,77],"been":[59,78],"implemented":[60],"dense":[64],"such":[66,87,94],"DGEMM":[68],"stencils,":[70],"is":[72,117],"the":[73,97,146],"first":[74],"instance":[75],"applied":[79],"comprehensively":[80],"to":[81,104,134],"bandwidth":[82],"intensive":[83,92],"complex":[85],"FFTs.":[90],"Bandwidth":[91],"optimizations":[93],"selecting":[96],"number":[98],"threads":[100],"inserting":[102],"padding":[103],"avoid":[105],"bank":[106],"conflicts":[107],"shared":[109],"memory":[110],"systematically":[112],"applied.":[113],"resulting":[115],"autotuner":[116],"fast":[118],"results":[120],"essentially":[124],"beats":[125],"all":[126],"a":[131],"single":[132],"processor":[133],"date,":[135],"moreover":[137],"exhibits":[138],"stable":[139],"irrespective":[141],"problem":[143],"or":[145],"underlying":[147],"GPU":[148],"hardware.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":23}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}