{"id":"https://openalex.org/W4239339525","doi":"https://doi.org/10.1109/pact.2000.888349","title":"Faster FFTs via architecture-cognizance","display_name":"Faster FFTs via architecture-cognizance","publication_year":2002,"publication_date":"2002-11-08","ids":{"openalex":"https://openalex.org/W4239339525","doi":"https://doi.org/10.1109/pact.2000.888349"},"language":"en","primary_location":{"id":"doi:10.1109/pact.2000.888349","doi":"https://doi.org/10.1109/pact.2000.888349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2000.888349","pdf_url":null,"source":{"id":"https://openalex.org/S4210194525","display_name":"International Conference on Parallel Architectures and Compilation Techniques (PACT)","issn_l":"1089-795X","issn":["1089-795X","2641-7944"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2000 International Conference on Parallel Architectures and Compilation Techniques (Cat. No.PR00622)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5071791092","display_name":"Kang Su Gatlin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kang Su Gatlin","raw_affiliation_strings":["Computer Science and Engineering Department, University of California, San Diego, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000216866","display_name":"L. Carter","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Carter","raw_affiliation_strings":["Computer Science and Engineering Department, University of California, San Diego, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.8027,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7286112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9970999956130981,"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":0.9970999956130981,"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":0.00139999995008111,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.0003000000142492354,"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":0.9160000085830688},{"id":"https://openalex.org/keywords/fftw","display_name":"FFTW","score":0.6389999985694885},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.4690000116825104},{"id":"https://openalex.org/keywords/parallel-fft","display_name":"parallel FFT","score":0.3610000014305115},{"id":"https://openalex.org/keywords/compiler-optimization","display_name":"compiler optimization","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8585733771324158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990334033966064},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7237598896026611},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6841587424278259},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6264795064926147},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6023286581039429},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5920814275741577},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5303372144699097},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42589062452316284},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31317049264907837},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18446633219718933},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1311524212360382},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pact.2000.888349","doi":"https://doi.org/10.1109/pact.2000.888349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2000.888349","pdf_url":null,"source":{"id":"https://openalex.org/S4210194525","display_name":"International Conference on Parallel Architectures and Compilation Techniques (PACT)","issn_l":"1089-795X","issn":["1089-795X","2641-7944"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2000 International Conference on Parallel Architectures and Compilation Techniques (Cat. No.PR00622)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1631114303","https://openalex.org/W1979219950","https://openalex.org/W2020214444","https://openalex.org/W2026237859","https://openalex.org/W2052977106","https://openalex.org/W2061171222","https://openalex.org/W2069173777","https://openalex.org/W2093582488","https://openalex.org/W2095875205","https://openalex.org/W2132986637","https://openalex.org/W2134572726","https://openalex.org/W2149103675","https://openalex.org/W2161539186","https://openalex.org/W2161938901","https://openalex.org/W2162169073","https://openalex.org/W2548341626","https://openalex.org/W2609112314","https://openalex.org/W4243796884"],"related_works":["https://openalex.org/W1559913899","https://openalex.org/W1725423100","https://openalex.org/W2159962438","https://openalex.org/W3197491507","https://openalex.org/W2096070062","https://openalex.org/W2074176412","https://openalex.org/W75626703","https://openalex.org/W7099080733","https://openalex.org/W4232570329","https://openalex.org/W178722281"],"abstract_inverted_index":{"The":[0,50],"Fast":[1],"Fourier":[2],"Transform":[3],"(FFT)":[4],"is":[5,29,52],"one":[6],"of":[7,19,91,106],"the":[8,38,65],"most":[9],"important":[10],"algorithms":[11],"in":[12,56],"computational":[13],"science,":[14],"accounting":[15],"for":[16,63],"large":[17,35],"amounts":[18],"computing":[20],"time.":[21],"One":[22],"major":[23],"problem":[24,39],"with":[25],"modern":[26],"FFT":[27,77],"implementations":[28],"that":[30],"they":[31],"poorly":[32],"scale":[33],"to":[34,72,108],"problem.":[36],"As":[37],"size":[40],"increases,":[41],"stride":[42],"and":[43,70,94,99],"associativity":[44],"effects":[45],"play":[46],"a":[47,53,61,74,100],"larger":[48],"role.":[49],"result":[51],"severe":[54],"drop-off":[55],"performance.":[57],"We":[58],"use":[59],"architecture-cognizance,":[60],"method":[62],"exploiting":[64],"interaction":[66],"between":[67],"architecture,":[68],"compiler,":[69],"algorithm,":[71],"create":[73],"more":[75],"scalable":[76],"package":[78],"based":[79],"on":[80,86],"FFTW.":[81],"Experiments":[82],"validate":[83],"our":[84],"approach":[85],"four":[87],"architectures:":[88],"two":[89],"generations":[90],"HPs":[92],"(PA-8000":[93],"8500),":[95],"an":[96],"IBM":[97],"POWER2,":[98],"DEC":[101],"Alpha":[102],"21164a.":[103],"Performance":[104],"increases":[105],"up":[107],"65%":[109],"are":[110],"obtained.":[111]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2022-05-12T00:00:00"}