{"id":"https://openalex.org/W3132558499","doi":"https://doi.org/10.1145/3437801.3441623","title":"FFT blitz","display_name":"FFT blitz","publication_year":2021,"publication_date":"2021-02-17","ids":{"openalex":"https://openalex.org/W3132558499","doi":"https://doi.org/10.1145/3437801.3441623","mag":"3132558499"},"language":"en","primary_location":{"id":"doi:10.1145/3437801.3441623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437801.3441623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5090785938","display_name":"Sultan Durrani","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sultan Durrani","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010527517","display_name":"Muhammad Saad Chughtai","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Saad Chughtai","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024517637","display_name":"Abdul Dakkak","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdul Dakkak","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-mei Hwu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056736926","display_name":"Lawrence Rauchwerger","orcid":"https://orcid.org/0000-0002-1545-4991"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence Rauchwerger","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"488","last_page":"489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9969000220298767,"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":0.9969000220298767,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12303","display_name":"Tensor decomposition and applications","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"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":0.9677932262420654},{"id":"https://openalex.org/keywords/split-radix-fft-algorithm","display_name":"Split-radix FFT algorithm","score":0.8481882810592651},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6991194486618042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6967852711677551},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5965715646743774},{"id":"https://openalex.org/keywords/prime-factor-fft-algorithm","display_name":"Prime-factor FFT algorithm","score":0.5778275728225708},{"id":"https://openalex.org/keywords/raders-fft-algorithm","display_name":"Rader's FFT algorithm","score":0.48953303694725037},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.45127856731414795},{"id":"https://openalex.org/keywords/twiddle-factor","display_name":"Twiddle factor","score":0.44881245493888855},{"id":"https://openalex.org/keywords/cooley\u2013tukey-fft-algorithm","display_name":"Cooley\u2013Tukey FFT algorithm","score":0.42932212352752686},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4234876036643982},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.41668978333473206},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.3976955711841583},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3897513449192047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1848195195198059},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.16613736748695374},{"id":"https://openalex.org/keywords/fractional-fourier-transform","display_name":"Fractional Fourier transform","score":0.0808020830154419},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.059632301330566406},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.05121144652366638}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.9677932262420654},{"id":"https://openalex.org/C103755468","wikidata":"https://www.wikidata.org/wiki/Q17103599","display_name":"Split-radix FFT algorithm","level":5,"score":0.8481882810592651},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6991194486618042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967852711677551},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5965715646743774},{"id":"https://openalex.org/C77928272","wikidata":"https://www.wikidata.org/wiki/Q7243214","display_name":"Prime-factor FFT algorithm","level":5,"score":0.5778275728225708},{"id":"https://openalex.org/C69598009","wikidata":"https://www.wikidata.org/wiki/Q7280126","display_name":"Rader's FFT algorithm","level":5,"score":0.48953303694725037},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.45127856731414795},{"id":"https://openalex.org/C4697666","wikidata":"https://www.wikidata.org/wiki/Q7857913","display_name":"Twiddle factor","level":5,"score":0.44881245493888855},{"id":"https://openalex.org/C1370844","wikidata":"https://www.wikidata.org/wiki/Q5167446","display_name":"Cooley\u2013Tukey FFT algorithm","level":3,"score":0.42932212352752686},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4234876036643982},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.41668978333473206},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.3976955711841583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3897513449192047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1848195195198059},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.16613736748695374},{"id":"https://openalex.org/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.0808020830154419},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.059632301330566406},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.05121144652366638},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3437801.3441623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437801.3441623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1966904279","https://openalex.org/W2061171222"],"related_works":["https://openalex.org/W1984254719","https://openalex.org/W2031343199","https://openalex.org/W2149121524","https://openalex.org/W2047042807","https://openalex.org/W2371538653","https://openalex.org/W2144412928","https://openalex.org/W2042527476","https://openalex.org/W4255785774","https://openalex.org/W2977460836","https://openalex.org/W2061302196"],"abstract_inverted_index":{"The":[0],"fast":[1],"Fourier":[2,11],"Transform":[3,12],"(FFT),":[4],"a":[5,27,66,115],"reduced-complexity":[6],"formulation":[7],"of":[8,21,38,43,50,93,99,117],"the":[9,39,44,59,71,75,82,83,97,109],"Discrete":[10],"(DFT),":[13],"is":[14,26,35],"an":[15],"important":[16],"tool":[17],"in":[18],"many":[19],"areas":[20],"science":[22],"and":[23,34,106],"engineering.":[24],"FFTW":[25,51],"well-known":[28],"package":[29],"that":[30,54,95,108],"follows":[31],"this":[32,62],"approach":[33,101,110],"currently":[36],"one":[37],"fastest":[40],"available":[41],"implementations":[42],"FFT.":[45],"NVIDIA":[46],"introduced":[47,77],"its":[48],"version":[49],"called":[52],"cuFFT":[53,113],"achieves":[55],"high":[56],"performance":[57,98],"on":[58,74,122],"GPUs.":[60],"In":[61],"work":[63],"we":[64],"present":[65,89],"novel":[67],"way":[68],"to":[69,120],"map":[70],"FFT":[72,86,104],"algorithm":[73],"newly":[76],"Tensor":[78],"Cores":[79],"by":[80],"adapting":[81],"Cooley-Tukey":[84],"recursive":[85],"algorithm.":[87],"We":[88],"four":[90],"major":[91],"types":[92],"optimizations":[94],"enhance":[96],"our":[100],"for":[102],"varying":[103],"sizes":[105],"show":[107],"consistently":[111],"outperforms":[112],"with":[114],"speedup":[116],"about":[118],"15%":[119],"250%":[121],"average.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-03-01T00:00:00"}