{"id":"https://openalex.org/W2159962438","doi":"https://doi.org/10.1109/ipdps.2009.5160995","title":"A performance model for Fast Fourier Transform","display_name":"A performance model for Fast Fourier Transform","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2159962438","doi":"https://doi.org/10.1109/ipdps.2009.5160995","mag":"2159962438"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2009.5160995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","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/A5100443879","display_name":"Yan Li","orcid":"https://orcid.org/0000-0002-4694-4926"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":["IBM China Research Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069454478","display_name":"Zhao Li","orcid":"https://orcid.org/0000-0002-3191-2278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Chinese Academy and Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy and Sciences, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029380103","display_name":"Haibo Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Lin","raw_affiliation_strings":["IBM China Research Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062592826","display_name":"Alex Chunghen Chow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Chunghen Chow","raw_affiliation_strings":["IBM Systems and Technology Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Systems and Technology Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082227710","display_name":"Jeffrey R. Diamond","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey R. Diamond","raw_affiliation_strings":["University of Texas, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9934999942779541,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.993399977684021,"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/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.9530519247055054},{"id":"https://openalex.org/keywords/split-radix-fft-algorithm","display_name":"Split-radix FFT algorithm","score":0.7662346959114075},{"id":"https://openalex.org/keywords/prime-factor-fft-algorithm","display_name":"Prime-factor FFT algorithm","score":0.7453838586807251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7383686900138855},{"id":"https://openalex.org/keywords/twiddle-factor","display_name":"Twiddle factor","score":0.5209878087043762},{"id":"https://openalex.org/keywords/raders-fft-algorithm","display_name":"Rader's FFT algorithm","score":0.5135748386383057},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4613744020462036},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4392293393611908},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4366295635700226},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.21645310521125793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1845880150794983}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.9530519247055054},{"id":"https://openalex.org/C103755468","wikidata":"https://www.wikidata.org/wiki/Q17103599","display_name":"Split-radix FFT algorithm","level":5,"score":0.7662346959114075},{"id":"https://openalex.org/C77928272","wikidata":"https://www.wikidata.org/wiki/Q7243214","display_name":"Prime-factor FFT algorithm","level":5,"score":0.7453838586807251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383686900138855},{"id":"https://openalex.org/C4697666","wikidata":"https://www.wikidata.org/wiki/Q7857913","display_name":"Twiddle factor","level":5,"score":0.5209878087043762},{"id":"https://openalex.org/C69598009","wikidata":"https://www.wikidata.org/wiki/Q7280126","display_name":"Rader's FFT algorithm","level":5,"score":0.5135748386383057},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4613744020462036},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4392293393611908},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4366295635700226},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.21645310521125793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1845880150794983},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2009.5160995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"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":29,"referenced_works":["https://openalex.org/W1584593027","https://openalex.org/W1631114303","https://openalex.org/W1766888123","https://openalex.org/W1966904279","https://openalex.org/W1990860452","https://openalex.org/W2000181170","https://openalex.org/W2008832322","https://openalex.org/W2022028092","https://openalex.org/W2059807497","https://openalex.org/W2061171222","https://openalex.org/W2088943630","https://openalex.org/W2096070062","https://openalex.org/W2102182691","https://openalex.org/W2103817093","https://openalex.org/W2106805276","https://openalex.org/W2123119012","https://openalex.org/W2124588455","https://openalex.org/W2127373103","https://openalex.org/W2127391977","https://openalex.org/W2134572726","https://openalex.org/W2135031801","https://openalex.org/W2136952590","https://openalex.org/W2164197394","https://openalex.org/W2569750427","https://openalex.org/W2685631283","https://openalex.org/W2764683856","https://openalex.org/W2904838066","https://openalex.org/W4254883682","https://openalex.org/W6756928340"],"related_works":["https://openalex.org/W1984254719","https://openalex.org/W2031343199","https://openalex.org/W2149121524","https://openalex.org/W2547585993","https://openalex.org/W2151986570","https://openalex.org/W2977460836","https://openalex.org/W2144412928","https://openalex.org/W2061302196","https://openalex.org/W2113951268","https://openalex.org/W1985279504"],"abstract_inverted_index":{"The":[0,31,47],"Fast":[1],"Fourier":[2],"Transform":[3],"(FFT)":[4],"has":[5],"been":[6],"considered":[7],"one":[8,110,386],"of":[9,44,49,65,156,200,238,241,254,265,271,281,323,346,349],"the":[10,52,62,66,104,112,133,153,163,197,215,226,231,239,260,279,344,350,374,388],"most":[11,32],"important":[12,24],"computing":[13],"algorithms":[14],"for":[15,27,121,136,312],"decades.":[16],"Its":[17],"vast":[18],"application":[19],"domain":[20],"makes":[21],"it":[22,175,341],"an":[23,263,308],"performance":[25,64,155,193,199,280,291,345,377],"benchmark":[26],"new":[28,157,185],"computer":[29],"architectures.":[30],"common":[33],"Cooley-Tukey":[34],"FFT":[35,40,72,80,99,119,154,198,248,310,354,376],"algorithm":[36],"factorizes":[37],"a":[38,42,77,95,122,137,180,184,191,201,236,244,251,269,282,297,301,313,347],"large":[39,67,138,252],"into":[41],"combination":[43],"smaller":[45],"ones.":[46],"choice":[48],"factors":[50,242],"and":[51,107,145],"order":[53,264],"in":[54,162,172,320,373,382],"which":[55,101,159,299],"they":[56],"are":[57,59,89,126],"applied":[58],"critical":[60],"to":[61,84,149,178,183,205,208,243,342],"ultimate":[63],"FFT.":[68,187,217],"Traditional":[69],"hand":[70,129,352],"coded":[71],"libraries":[73],"can":[74,276,317],"immediately":[75],"execute":[76],"given":[78,123,202,268,314],"sized":[79,186,295],"applying":[81],"constant":[82],"heuristics":[83],"different":[85],"kernel":[86],"sizes,":[87],"but":[88],"not":[90],"always":[91],"optimal.":[92],"FFTW":[93],"is":[94,146,160,167,176],"popular":[96],"auto":[97],"tuning":[98],"library":[100,355],"searches":[102],"over":[103],"possible":[105],"factorizations":[106],"empirically":[108],"determines":[109],"with":[111,128,369],"best":[113],"performance.":[114],"This":[115,188],"search":[116,134,232,261],"method":[117],"produces":[118],"kernels":[120,381],"size":[124,139,204,234,316],"that":[125,195],"competitive":[127],"tuned":[130,353],"libraries.":[131],"Unfortunately,":[132],"process":[135,298],"takes":[140,300],"hours":[141],"on":[142,293],"real":[143],"hardware,":[144],"completely":[147,277],"infeasible":[148],"use":[150],"when":[151],"evaluating":[152],"hardware":[158],"still":[161],"simulation":[164],"phase.":[165],"It":[166],"also":[168],"less":[169],"than":[170],"ideal":[171],"environments":[173],"where":[174],"desirable":[177],"have":[179],"rapid":[181],"response":[182],"paper":[189],"introduces":[190],"novel":[192],"model":[194,229,275],"allows":[196],"data":[203],"be":[206,318],"estimated":[207],"within":[209,225],"2%":[210],"error":[211],"without":[212],"ever":[213],"running":[214,288],"actual":[216],"In":[218,325],"addition,":[219],"by":[220,262,286,339,356,363],"recognizing":[221],"more":[222],"sophisticated":[223],"patterns":[224],"computation,":[227],"this":[228,257,274,326],"reduces":[230,259],"tree":[233],"from":[235],"permutation":[237],"number":[240,253],"combination.":[245],"Because":[246],"typical":[247],"sizes":[249],"contain":[250],"similar":[255],"factors,":[256],"effectively":[258],"magnitude.":[266],"When":[267],"set":[270],"computational":[272],"kernels,":[273],"characterize":[278],"chosen":[283],"target":[284],"architecture":[285],"just":[287],"some":[289],"short":[290],"tests":[292],"each":[294],"kernel,":[296],"few":[302],"minutes":[303],"or":[304],"less.":[305],"Once":[306],"characterized,":[307],"optimal":[309],"plan":[311],"input":[315],"determined":[319],"milliseconds":[321],"instead":[322],"hours.":[324],"paper,":[327],"we":[328,359],"first":[329],"derive":[330],"our":[331,370],"mathematical":[332],"model.":[333],"We":[334],"then":[335],"validate":[336],"its":[337,361],"accuracy":[338],"using":[340,378],"improve":[343],"state":[348],"art,":[351],"30%.":[357],"Finally,":[358],"demonstrate":[360],"effectiveness":[362],"replacing":[364],"FFTWs":[365,379],"own":[366,380],"planning":[367],"stage":[368],"model,":[371],"resulting":[372],"same":[375],"as":[383,385],"little":[384],"millionth":[387],"computation":[389],"time.":[390]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}