{"id":"https://openalex.org/W1976170135","doi":"https://doi.org/10.1177/1094342004041292","title":"Automatic Performance Tuning for Fast Fourier Transforms","display_name":"Automatic Performance Tuning for Fast Fourier Transforms","publication_year":2004,"publication_date":"2004-02-01","ids":{"openalex":"https://openalex.org/W1976170135","doi":"https://doi.org/10.1177/1094342004041292","mag":"1976170135"},"language":"en","primary_location":{"id":"doi:10.1177/1094342004041292","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342004041292","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/A5098409014","display_name":"Dragan Mirkovi","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dragan Mirkovi\\#263;","raw_affiliation_strings":["Dept of Computer Science, University of Houston, Houston, TX 77204, USA"],"affiliations":[{"raw_affiliation_string":"Dept of Computer Science, University of Houston, Houston, TX 77204, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073745784","display_name":"Lennart Johnsson","orcid":"https://orcid.org/0000-0003-0337-879X"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lennart Johnsson","raw_affiliation_strings":["DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF HOUSTON, HOUSTON, TX 77204, USA"],"affiliations":[{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF HOUSTON, HOUSTON, TX 77204, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5098409014"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.12663143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":"47","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9991999864578247,"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/T11417","display_name":"Advancements in PLL and VCO Technologies","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11873","display_name":"PAPR reduction in OFDM","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7998942136764526},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7969363331794739},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.6038665771484375},{"id":"https://openalex.org/keywords/microprocessor","display_name":"Microprocessor","score":0.591211199760437},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.572227954864502},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.5431545972824097},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5085166692733765},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5018351078033447},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4916577935218811},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.47872233390808105},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4770090579986572},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.47476768493652344},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3833892345428467},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3330667018890381},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.28158268332481384},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2594870328903198},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19413882493972778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11941462755203247},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10311678051948547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07398951053619385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998942136764526},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7969363331794739},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.6038665771484375},{"id":"https://openalex.org/C2780728072","wikidata":"https://www.wikidata.org/wiki/Q5297","display_name":"Microprocessor","level":2,"score":0.591211199760437},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.572227954864502},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.5431545972824097},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5085166692733765},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5018351078033447},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4916577935218811},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.47872233390808105},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4770090579986572},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.47476768493652344},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3833892345428467},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3330667018890381},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.28158268332481384},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2594870328903198},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19413882493972778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11941462755203247},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10311678051948547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07398951053619385},{"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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342004041292","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342004041292","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320308380","display_name":"Yale University","ror":"https://ror.org/03v76x132"},{"id":"https://openalex.org/F4320309622","display_name":"Harvard University","ror":"https://ror.org/03vek6s52"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W5043811","https://openalex.org/W1516217143","https://openalex.org/W1631114303","https://openalex.org/W1966904279","https://openalex.org/W1990357034","https://openalex.org/W2061171222","https://openalex.org/W2096070062","https://openalex.org/W2106805276","https://openalex.org/W2123119012","https://openalex.org/W2129508707","https://openalex.org/W2134572726","https://openalex.org/W2164197394","https://openalex.org/W2904838066","https://openalex.org/W4299345789","https://openalex.org/W6679308754"],"related_works":["https://openalex.org/W650988184","https://openalex.org/W2162410319","https://openalex.org/W4321184925","https://openalex.org/W60915090","https://openalex.org/W2025840053","https://openalex.org/W2161692994","https://openalex.org/W4320560513","https://openalex.org/W2146865435","https://openalex.org/W4225492247","https://openalex.org/W2137356287"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"discuss":[4],"architecture-specific":[5],"performance":[6,72],"tuning":[7],"for":[8,28,49,74],"fast":[9],"Fourier":[10],"transforms":[11],"(FFTs)":[12],"implemented":[13],"in":[14],"the":[15,32,36,45,50,57,63,71],"UHFFT":[16,19],"library.":[17],"The":[18],"library":[20,27,51],"is":[21],"an":[22],"adaptive":[23],"and":[24,54,60],"portable":[25],"software":[26],"FFTs":[29],"developed":[30],"by":[31],"authors.":[33],"We":[34,68],"present":[35],"optimization":[37,66],"methods":[38],"used":[39,48],"at":[40],"different":[41],"levels,":[42],"starting":[43],"with":[44,56],"algorithm":[46],"selection":[47],"code":[52],"generation":[53],"ending":[55],"actual":[58],"implementation":[59],"specification":[61],"of":[62],"appropriate":[64],"compiler":[65],"options.":[67],"report":[69],"on":[70],"results":[73],"several":[75],"modern":[76],"microprocessor":[77],"architectures.":[78]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
