{"id":"https://openalex.org/W1555087507","doi":"https://doi.org/10.1109/ipdps.2003.1213153","title":"Short vector code generation for the discrete Fourier transform","display_name":"Short vector code generation for the discrete Fourier transform","publication_year":2004,"publication_date":"2004-03-22","ids":{"openalex":"https://openalex.org/W1555087507","doi":"https://doi.org/10.1109/ipdps.2003.1213153","mag":"1555087507"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2003.1213153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2003.1213153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings International Parallel and Distributed Processing Symposium","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/A5062806943","display_name":"Franz Franchetti","orcid":"https://orcid.org/0000-0002-3529-8973"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]},{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"F. Franchetti","raw_affiliation_strings":["Applied and Numerical Mathematics, Technical University of of Vienna, Austria","Tech. Univ. of Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied and Numerical Mathematics, Technical University of of Vienna, Austria","institution_ids":[]},{"raw_affiliation_string":"Tech. Univ. of Vienna, Austria","institution_ids":["https://openalex.org/I129774422","https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076407181","display_name":"Markus P\u00fcschel","orcid":"https://orcid.org/0000-0001-8834-8551"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Puschel","raw_affiliation_strings":["Electrical and Computer Engineering, Carnegie Mellon University, USA","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11417","display_name":"Advancements in PLL and VCO Technologies","score":0.9976000189781189,"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":0.7098001837730408},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5863852500915527},{"id":"https://openalex.org/keywords/pentium","display_name":"Pentium","score":0.5310044288635254},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.5133199095726013},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5014553070068359},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.46223360300064087},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.45682385563850403},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4499286115169525},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4417590796947479},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.44105035066604614},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39703693985939026},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23936223983764648},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.20563623309135437},{"id":"https://openalex.org/keywords/fractional-fourier-transform","display_name":"Fractional Fourier transform","score":0.19931501150131226},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19215449690818787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098001837730408},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5863852500915527},{"id":"https://openalex.org/C46268123","wikidata":"https://www.wikidata.org/wiki/Q214314","display_name":"Pentium","level":2,"score":0.5310044288635254},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.5133199095726013},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5014553070068359},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.46223360300064087},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.45682385563850403},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4499286115169525},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4417590796947479},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.44105035066604614},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39703693985939026},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23936223983764648},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.20563623309135437},{"id":"https://openalex.org/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.19931501150131226},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19215449690818787},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ipdps.2003.1213153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2003.1213153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings International Parallel and Distributed Processing Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.7329","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.7329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.cmu.edu/~pueschel/papers/fftsimd.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.203.1117","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.203.1117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.cmu.edu/~pueschel/papers/fftsimd.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1523329529","https://openalex.org/W1820775600","https://openalex.org/W1990860452","https://openalex.org/W2045810654","https://openalex.org/W2046812923","https://openalex.org/W2072277531","https://openalex.org/W2096070062","https://openalex.org/W2138289268","https://openalex.org/W2140080674","https://openalex.org/W2163491234","https://openalex.org/W3150704386","https://openalex.org/W6662507073"],"related_works":["https://openalex.org/W1597195064","https://openalex.org/W1545378222","https://openalex.org/W2915007006","https://openalex.org/W3164835776","https://openalex.org/W2230641373","https://openalex.org/W1560501822","https://openalex.org/W2129938370","https://openalex.org/W1802594910","https://openalex.org/W2618542445","https://openalex.org/W2019264056"],"abstract_inverted_index":{"In":[0],"this":[1,42,93],"paper":[2],"we":[3,44,67],"use":[4],"a":[5,31,37,47,50,69],"mathematical":[6,32],"approach":[7,94],"to":[8],"automatically":[9,108],"generate":[10,45],"high":[11],"performance":[12],"short":[13,63],"vector":[14,39,64,70,113],"code":[15,71,114],"for":[16,46,84],"the":[17,24,79,85,88,98,118],"discrete":[18],"Fourier":[19,28],"transform":[20,29],"(DFT).":[21],"We":[22,91],"represent":[23],"well-known":[25],"Cooley-Tukey":[26],"fast":[27],"in":[30,78],"notation":[33],"and":[34,59,105,111],"formally":[35],"derive":[36],"\"short":[38],"variant\".":[40],"Using":[41],"recursion":[43],"given":[48,89],"DFT":[49],"large":[51],"number":[52],"of":[53,81,97],"different":[54,82],"algorithms,":[55],"represented":[56],"as":[57,95],"formulas,":[58],"translate":[60],"them":[61],"into":[62],"code.":[65],"Then":[66],"present":[68],"specific":[72],"dynamic":[73],"programming":[74],"method":[75],"that":[76],"searches":[77],"space":[80],"implementations":[83],"fastest":[86],"on":[87],"architecture.":[90],"implemented":[92],"part":[96],"SPIRAL":[99],"library":[100],"generator":[101],"On":[102],"Pentium":[103],"III":[104],"4,":[106],"our":[107],"generated":[109],"SSE":[110],"SSE2":[112],"compares":[115],"favorably":[116],"with":[117],"hand-tuned":[119],"Intel":[120],"vendor":[121],"library.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
