{"id":"https://openalex.org/W2071739952","doi":"https://doi.org/10.1145/2159430.2159437","title":"High performance 3-D FFT using multiple CUDA GPUs","display_name":"High performance 3-D FFT using multiple CUDA GPUs","publication_year":2012,"publication_date":"2012-03-03","ids":{"openalex":"https://openalex.org/W2071739952","doi":"https://doi.org/10.1145/2159430.2159437","mag":"2071739952"},"language":"en","primary_location":{"id":"doi:10.1145/2159430.2159437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2159430.2159437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Nukada","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017088569","display_name":"Yutaka Maruyama","orcid":"https://orcid.org/0000-0003-4035-4885"},"institutions":[{"id":"https://openalex.org/I4210143791","display_name":"Institute for Molecular Science","ror":"https://ror.org/04wqh5h97","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I199525922","https://openalex.org/I4210143791"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yutaka Maruyama","raw_affiliation_strings":["Institute for Molecular Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Molecular Science","institution_ids":["https://openalex.org/I4210143791"]}]},{"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/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/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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["Tokyo Institute of Technology/National Institute of Informatics","Tokyo Institute of Technology / National Institute of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology/National Institute of Informatics","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of Technology / National Institute of Informatics","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":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9951000213623047,"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":0.9951000213623047,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8885209560394287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8067009449005127},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7984791994094849},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7524673938751221},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5450587272644043},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.43215417861938477},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4301305413246155},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.41040223836898804},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19007116556167603},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1384192705154419},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.13335072994232178}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8885209560394287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8067009449005127},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7984791994094849},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7524673938751221},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5450587272644043},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.43215417861938477},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4301305413246155},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.41040223836898804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19007116556167603},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1384192705154419},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.13335072994232178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2159430.2159437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2159430.2159437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G5125938736","display_name":"Fault Tolerant Infrastructure Toward Billion of Parallelization and Exa-scale Supercomputer","funder_award_id":"23220003","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2016677154","https://openalex.org/W2045629276","https://openalex.org/W2061171222","https://openalex.org/W2107483876","https://openalex.org/W2108600626","https://openalex.org/W2114927422","https://openalex.org/W2155503253","https://openalex.org/W2158261096","https://openalex.org/W2334899772","https://openalex.org/W2481321346","https://openalex.org/W6654554885","https://openalex.org/W6721582261"],"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":{"Fast":[0],"Fourier":[1],"transform":[2],"is":[3],"one":[4],"of":[5,14,21,39,65],"the":[6,37,40,67],"most":[7],"important":[8],"computations":[9],"used":[10],"in":[11],"many":[12],"kinds":[13],"applications.":[15],"Although":[16],"there":[17],"are":[18],"several":[19],"works":[20],"on":[22,54,59],"single":[23,56,78],"GPU":[24,51,74],"FFT,":[25],"we":[26],"also":[27],"need":[28],"large-scale":[29],"transforms":[30],"that":[31],"require":[32],"multiple":[33,50,60],"GPUs":[34],"due":[35],"to":[36],"capacity":[38],"device":[41],"memory.":[42],"We":[43],"present":[44],"high":[45],"performance":[46],"3-D":[47],"FFT":[48,75],"using":[49],"devices":[52],"both":[53],"a":[55,63],"node":[57],"and":[58],"nodes.":[61],"As":[62],"result":[64],"optimizing":[66],"data":[68],"transfer":[69],"between":[70],"GPUs,":[71],"our":[72],"multi":[73],"successfully":[76],"outperform":[77],"GPU.":[79]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}