{"id":"https://openalex.org/W2108600626","doi":"https://doi.org/10.5555/1413370.1413373","title":"High performance discrete Fourier transforms on graphics processors","display_name":"High performance discrete Fourier transforms on graphics processors","publication_year":2008,"publication_date":"2008-11-15","ids":{"openalex":"https://openalex.org/W2108600626","doi":"https://doi.org/10.5555/1413370.1413373","mag":"2108600626"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.566.425","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.566.425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csd.uwo.ca/~moreno/CS433-CS9624/Resources/DiscreteFourierTransformsonGPUs.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5049041008","display_name":"Naga K. Govindaraju","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naga K. Govindaraju","raw_affiliation_strings":["MICROSOFT CORP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MICROSOFT CORP","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032912716","display_name":"Brandon Lloyd","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brandon Lloyd","raw_affiliation_strings":["MICROSOFT CORP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MICROSOFT CORP","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027225480","display_name":"Yuri Dotsenko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuri Dotsenko","raw_affiliation_strings":["MICROSOFT CORP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MICROSOFT CORP","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113682703","display_name":"Burton J. Smith","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Burton Smith","raw_affiliation_strings":["MICROSOFT CORP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MICROSOFT CORP","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021080394","display_name":"John L. Manferdelli","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Manferdelli","raw_affiliation_strings":["MICROSOFT CORP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MICROSOFT CORP","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":32.4647,"has_fulltext":false,"cited_by_count":244,"citation_normalized_percentile":{"value":0.99770951,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9253000020980835,"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":0.9253000020980835,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.06030000001192093,"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"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.0013000000035390258,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"discrete Fourier transform","score":0.9810000061988831},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.859000027179718},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"fast Fourier transform","score":0.6620000004768372},{"id":"https://openalex.org/keywords/mixed-radix-fft","display_name":"mixed-radix FFT","score":0.8799999952316284},{"id":"https://openalex.org/keywords/shared-memory","display_name":"shared memory","score":0.7910000085830688},{"id":"https://openalex.org/keywords/modular-arithmetic","display_name":"modular arithmetic","score":0.8970000147819519},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6790000200271606},{"id":"https://openalex.org/keywords/cufft","display_name":"cuFFT","score":0.7760000228881836},{"id":"https://openalex.org/keywords/multiple-kernel-learning","display_name":"multiple kernel learning","score":0.6129999756813049},{"id":"https://openalex.org/keywords/performance-comparison","display_name":"performance comparison","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883270978927612},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7855185270309448},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.7017587423324585},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5678266286849976},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5200793147087097},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.44458267092704773},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4418080151081085},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.566.425","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.566.425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csd.uwo.ca/~moreno/CS433-CS9624/Resources/DiscreteFourierTransformsonGPUs.pdf","raw_type":"text"},{"id":"mag:2108600626","doi":"https://doi.org/10.5555/1413370.1413373","is_oa":false,"landing_page_url":"https://mc.stanford.edu/cgi-bin/images/7/75/SC08_FFT_on_GPUs.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418683","display_name":"IEEE International Conference on High Performance Computing, Data, and Analytics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on High Performance Computing, Data, and Analytics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W16218651","https://openalex.org/W205547992","https://openalex.org/W1564601597","https://openalex.org/W2016677154","https://openalex.org/W2045836768","https://openalex.org/W2077110374","https://openalex.org/W2108157916","https://openalex.org/W2108792719","https://openalex.org/W2124588455","https://openalex.org/W2134572726","https://openalex.org/W2140856831"],"related_works":["https://openalex.org/W7097372711","https://openalex.org/W4411196776","https://openalex.org/W2142388621","https://openalex.org/W7100843566","https://openalex.org/W2784930005","https://openalex.org/W2557001747","https://openalex.org/W2343773275","https://openalex.org/W2745695744","https://openalex.org/W6974540822","https://openalex.org/W2097477621"],"abstract_inverted_index":{"Abstract\u2014We":[0],"present":[1,15],"novel":[2],"algorithms":[3,20,30,49,90],"for":[4,21,141],"computing":[5],"discrete":[6],"Fourier":[7],"transforms":[8],"with":[9,100,127],"high":[10],"performance":[11,99,121,129],"on":[12,35,110],"GPUs.":[13],"We":[14,41,76,87],"hierarchical,":[16],"mixed":[17,67],"radix":[18,68],"FFT":[19,29],"both":[22],"power-of-two":[23],"and":[24,73,96,104,136],"non-power-of-two":[25,60],"sizes.":[26,143],"Our":[27],"hierarchical":[28,48],"efficiently":[31],"exploit":[32],"shared":[33],"memory":[34,44],"GPUs":[36],"using":[37,91],"a":[38,55,64,111],"Stockham":[39],"formulation.":[40],"reduce":[42],"the":[43,52,85,92],"transpose":[45],"overheads":[46],"in":[47,80],"by":[50],"combining":[51],"transposes":[53],"into":[54],"block-based":[56],"multi-FFT":[57],"algorithm.":[58,75],"For":[59],"sizes,":[61],"we":[62,119],"use":[63,77],"combination":[65],"of":[66,70,122,131],"FFTs":[69],"small":[71],"primes":[72],"Bluestein\u2019s":[74,81],"modular":[78],"arithmetic":[79],"algorithm":[82],"to":[83,124],"improve":[84],"accuracy.":[86],"implemented":[88],"our":[89],"NVIDIA":[93,117],"CUDA":[94],"API":[95],"compared":[97],"their":[98],"NVIDIA\u2019s":[101],"CUFFT":[102,135],"library":[103],"an":[105,116],"optimized":[106],"CPU-implementation":[107],"(Intel\u2019s":[108],"MKL)":[109],"high-end":[112],"quad-core":[113],"CPU.":[114],"On":[115],"GPU,":[118],"obtained":[120],"up":[123],"300":[125],"GFlops,":[126],"typical":[128],"improvements":[130],"2\u20134":[132],"\u00d7":[133],"over":[134,139],"8\u201340\u00d7":[137],"improvement":[138],"MKL":[140],"large":[142],"I.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":25},{"year":2013,"cited_by_count":32},{"year":2012,"cited_by_count":22}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}