{"id":"https://openalex.org/W1963990117","doi":"https://doi.org/10.1177/1094342011435158","title":"Large-scale fast Fourier transform on a heterogeneous multi-core system","display_name":"Large-scale fast Fourier transform on a heterogeneous multi-core system","publication_year":2012,"publication_date":"2012-03-18","ids":{"openalex":"https://openalex.org/W1963990117","doi":"https://doi.org/10.1177/1094342011435158","mag":"1963990117"},"language":"en","primary_location":{"id":"doi:10.1177/1094342011435158","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342011435158","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-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/A5100443879","display_name":"Yan Li","orcid":"https://orcid.org/0000-0002-4694-4926"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":["IBM China Research Lab, China","IBM, China Research Lab., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Lab, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM, China Research Lab., China","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","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 at Austin, Austin, TX, USA","University of Texas at Austin, Austin, TX USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, Austin, TX USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407848","display_name":"Xu Wang","orcid":"https://orcid.org/0000-0002-1492-3477"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Xu Wang","raw_affiliation_strings":["IBM China Research Lab, China","IBM, China Research Lab., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Lab, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM, China Research Lab., China","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029380103","display_name":"Haibo Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Haibo Lin","raw_affiliation_strings":["IBM China Research Lab, China","IBM, China Research Lab., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Lab, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM, China Research Lab., China","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063880588","display_name":"Yudong Yang","orcid":"https://orcid.org/0000-0002-8546-8678"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yudong Yang","raw_affiliation_strings":["IBM Systems Technology Group, China","IBM Systems Technology Group, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Systems Technology Group, China","institution_ids":[]},{"raw_affiliation_string":"IBM Systems Technology Group, China#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064049610","display_name":"Zhenxing Han","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenxing Han","raw_affiliation_strings":["IBM Systems Technology Group, China","IBM Systems Technology Group, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Systems Technology Group, China","institution_ids":[]},{"raw_affiliation_string":"IBM Systems Technology Group, China#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100407848"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210126794"],"apc_list":null,"apc_paid":null,"fwci":0.869,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71749792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"26","issue":"2","first_page":"148","last_page":"158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9950000047683716,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.991100013256073,"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":0.9077086448669434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7920510768890381},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6038376092910767},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5690510869026184},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4386771619319916},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3558621406555176},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30405521392822266},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18955257534980774}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.9077086448669434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920510768890381},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6038376092910767},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5690510869026184},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4386771619319916},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3558621406555176},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30405521392822266},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18955257534980774},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342011435158","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342011435158","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W6186695","https://openalex.org/W31797265","https://openalex.org/W1564601597","https://openalex.org/W1966904279","https://openalex.org/W1998006081","https://openalex.org/W2004511788","https://openalex.org/W2011191879","https://openalex.org/W2061171222","https://openalex.org/W2096070062","https://openalex.org/W2103817093","https://openalex.org/W2124588455","https://openalex.org/W2131958140","https://openalex.org/W2136952590","https://openalex.org/W2140698245","https://openalex.org/W2159962438","https://openalex.org/W2164197394","https://openalex.org/W2165288094","https://openalex.org/W2537233909"],"related_works":["https://openalex.org/W4327521644","https://openalex.org/W2111241003","https://openalex.org/W2978884468","https://openalex.org/W3132558499","https://openalex.org/W2168413811","https://openalex.org/W2005846134","https://openalex.org/W4200391368","https://openalex.org/W2355315220","https://openalex.org/W4367355863","https://openalex.org/W2405661381"],"abstract_inverted_index":{"As":[0],"interest":[1,32],"in":[2,33,57,119,135,180,268,296],"hybrid":[3],"computing":[4],"systems":[5,256],"increases,":[6],"people":[7],"are":[8,257],"eager":[9],"to":[10,14,86,166,261,275,299],"find":[11],"new":[12],"ways":[13],"exploit":[15],"the":[16,23,58,97,103,136,170,239,250],"unique":[17],"and":[18,138,160,163,225,247],"efficient":[19,88],"computational":[20],"power":[21],"of":[22,44,61,129,169,190,207,216],"heterogeneous":[24,80,104,251],"multi-core":[25,81,105,252],"systems.":[26],"Although":[27],"there":[28],"has":[29],"been":[30],"much":[31,70],"implementing":[34],"high-performance":[35],"fast":[36],"Fourier":[37,133],"transform":[38],"(FFT)":[39],"libraries":[40,48],"on":[41,50,187,293],"this":[42,93,181,188,208,269,297],"kind":[43,189],"system,":[45],"most":[46],"existing":[47],"focus":[49],"small-scale":[51],"FFTs":[52,114],"whose":[53],"data":[54,158,194],"can":[55,111,271],"fit":[56],"local":[59,171,283],"storage":[60,172,284],"a":[62,120],"single":[63,121,142],"accelerator.":[64,122],"Real-world":[65],"FFT":[66,90,100,144,156,186],"applications":[67],"often":[68],"require":[69],"larger":[71,115],"scale":[72],"FFTs,":[73],"but":[74],"it":[75,237],"is":[76,183,198,210],"extremely":[77],"challenging":[78],"for":[79,102,154,212,249],"system":[82,106],"with":[83,107,243],"distributed":[84,108],"architectures":[85,277],"make":[87],"large":[89],"implementations.":[91],"In":[92],"paper,":[94],"we":[95,219],"introduce":[96],"first":[98],"known":[99],"library":[101],"architecture":[109,191],"that":[110,184,211],"solve":[112],"one-dimensional":[113],"than":[116],"what":[117],"fits":[118],"Our":[123],"implementation":[124],"achieves":[125],"67%":[126],"performance":[127,150,228],"improvement":[128],"FFTW":[130],"3.2.2":[131],"(Fastest":[132],"Transform":[134],"West)":[137],"sustains":[139],"over":[140],"36":[141],"precision":[143],"GFLOPs":[145],"\u2018end-to-end\u2019":[146],"Achieving":[147],"such":[148],"high":[149],"requires":[151],"novel":[152],"schemes":[153],"large-scale":[155,185],"factorization,":[157],"permutation":[159],"all-to-all":[161],"exchanges,":[162],"buffer":[164],"designs":[165],"maximize":[167],"use":[168],"while":[173],"minimizing":[174],"communication":[175,245],"overhead.":[176],"One":[177],"important":[178],"finding":[179],"paper":[182,209,270,298],"behaves":[192],"as":[193,236],"transfer":[195],"bound":[196],"which":[197],"quite":[199],"different":[200,244],"from":[201],"other":[202],"architectures.":[203,301],"A":[204],"significant":[205],"contribution":[206],"each":[213],"major":[214],"component":[215],"our":[217],"algorithm,":[218],"explore":[220],"many":[221],"possible":[222],"design":[223],"options":[224],"present":[226],"quantitative":[227],"comparisons.":[229],"This":[230],"provides":[231],"value":[232],"beyond":[233],"specific":[234],"architecture,":[235],"illustrates":[238],"fundamental":[240],"features":[241],"associated":[242],"paradigms":[246],"mechanisms":[248],"system.":[253],"Today\u2019s":[254],"computer":[255],"increasingly":[258],"being":[259],"designed":[260],"include":[262],"general":[263],"purpose":[264],"accelerators.":[265],"The":[266],"techniques":[267,295],"also":[272,290],"be":[273],"applied":[274],"these":[276],"especially":[278],"when":[279],"they":[280],"have":[281],"limited":[282],"or":[285],"steep":[286],"cache":[287],"hierarchies.":[288],"We":[289],"provide":[291],"insights":[292],"applying":[294],"similar":[300]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
