{"id":"https://openalex.org/W2009516879","doi":"https://doi.org/10.1145/1810085.1810127","title":"An empirically tuned 2D and 3D FFT library on CUDA GPU","display_name":"An empirically tuned 2D and 3D FFT library on CUDA GPU","publication_year":2010,"publication_date":"2010-06-02","ids":{"openalex":"https://openalex.org/W2009516879","doi":"https://doi.org/10.1145/1810085.1810127","mag":"2009516879"},"language":"en","primary_location":{"id":"doi:10.1145/1810085.1810127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1810085.1810127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International Conference on Supercomputing","raw_type":"proceedings-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/A5064828315","display_name":"Liang Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liang Gu","raw_affiliation_strings":["University of Delaware, Newark, DE"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452133","display_name":"Xiaoming Li","orcid":"https://orcid.org/0000-0002-7397-723X"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoming Li","raw_affiliation_strings":["University of Delaware, Newark, DE"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027240262","display_name":"Jakob Siegel","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jakob Siegel","raw_affiliation_strings":["University of Delaware, Newark, DE"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064828315"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":4.9937,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95605666,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9937999844551086,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9907000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.9086635112762451},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8362621068954468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8183290958404541},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.727340579032898},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5573289394378662},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4835929274559021},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4150354564189911},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2544771432876587},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22993549704551697}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.9086635112762451},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8362621068954468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183290958404541},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.727340579032898},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5573289394378662},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4835929274559021},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4150354564189911},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2544771432876587},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22993549704551697}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1810085.1810127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1810085.1810127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2016677154","https://openalex.org/W2022028092","https://openalex.org/W2102182691","https://openalex.org/W2107483876","https://openalex.org/W2108600626","https://openalex.org/W2108792719","https://openalex.org/W2108872752","https://openalex.org/W2114927422","https://openalex.org/W2123881099","https://openalex.org/W2134572726","https://openalex.org/W2136952590","https://openalex.org/W2164197394","https://openalex.org/W3004184795"],"related_works":["https://openalex.org/W3213381848","https://openalex.org/W2017587301","https://openalex.org/W2012954338","https://openalex.org/W2005148983","https://openalex.org/W2096672917","https://openalex.org/W2009169896","https://openalex.org/W2392023973","https://openalex.org/W2939411666","https://openalex.org/W3189307731","https://openalex.org/W2949962288"],"abstract_inverted_index":{"In":[0,55],"this":[1,113],"paper,":[2],"a":[3,33,119],"Cooley-Tukey":[4],"algorithm":[5],"based":[6],"multidimensional":[7],"FFT":[8,22,38,51,122],"computation":[9],"framework":[10,16,43,130],"on":[11,23,40,52,138],"GPU":[12,53],"is":[13,44,62],"proposed.":[14],"This":[15],"generalizes":[17],"the":[18,47,80,87],"decomposition":[19],"of":[20,36,49,71,82,89,98],"multi-dimensional":[21,50],"GPUs":[24],"using":[25],"an":[26],"I/O":[27],"tensor":[28],"representation,":[29],"and":[30,64,69,85,96,106,131],"therefore":[31],"provides":[32],"systematic":[34],"description":[35],"possible":[37],"implementations":[39],"GPUs.":[41,139],"The":[42],"geared":[45],"to":[46,78],"efficiency":[48],"architectures.":[54],"particular,":[56],"no":[57],"global":[58,90],"transposition":[59],"among":[60],"dimensions":[61,73],"performed":[63],"some":[65],"previously":[66],"unnoticed":[67],"grouping":[68],"commutability":[70],"multiple":[72],"are":[74,109,135],"highlighted":[75],"in":[76,112,126],"order":[77],"reduce":[79],"number":[81,88],"computational":[83],"kernels":[84],"minimize":[86],"memory":[91],"accesses.":[92],"Important":[93],"architectural":[94],"factors":[95],"constraints":[97],"CUDA,":[99],"such":[100],"as":[101],"coalesced":[102],"access,":[103],"bank":[104],"conflicts":[105],"register":[107],"pressure":[108],"also":[110],"considered":[111],"framework.":[114],"Moreover,":[115],"we":[116],"adapt":[117],"codelets,":[118],"straight-line":[120],"style":[121],"implementation":[123],"originally":[124],"developed":[125],"FFTW,":[127],"into":[128],"our":[129],"prove":[132],"that":[133],"they":[134],"highly":[136],"efficient":[137]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}