{"id":"https://openalex.org/W2146236588","doi":"https://doi.org/10.1145/1188455.1188575","title":"Tools and techniques for performance---FFT program generation for shared memory","display_name":"Tools and techniques for performance---FFT program generation for shared memory","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2146236588","doi":"https://doi.org/10.1145/1188455.1188575","mag":"2146236588"},"language":"en","primary_location":{"id":"doi:10.1145/1188455.1188575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1188455.1188575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing - SC '06","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/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":"Franz Franchetti","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077820779","display_name":"Yevgen Voronenko","orcid":null},"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":"Yevgen Voronenko","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"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":"Markus P\u00fcschel","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9990000128746033,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.7704432010650635},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5123230218887329},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.5098680257797241},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40267103910446167},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39054712653160095},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3712158799171448},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12005877494812012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704432010650635},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5123230218887329},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.5098680257797241},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40267103910446167},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39054712653160095},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3712158799171448},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12005877494812012}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1188455.1188575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1188455.1188575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing - SC '06","raw_type":"proceedings-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/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1504164230","https://openalex.org/W1540992910","https://openalex.org/W1543833969","https://openalex.org/W1555087507","https://openalex.org/W1556859836","https://openalex.org/W1910724553","https://openalex.org/W1964031104","https://openalex.org/W1973305402","https://openalex.org/W1974470587","https://openalex.org/W2004711550","https://openalex.org/W2037929850","https://openalex.org/W2045810654","https://openalex.org/W2045836768","https://openalex.org/W2046812923","https://openalex.org/W2047656763","https://openalex.org/W2072277531","https://openalex.org/W2097753256","https://openalex.org/W2102182691","https://openalex.org/W2106472852","https://openalex.org/W2112482891","https://openalex.org/W2119609467","https://openalex.org/W2130289795","https://openalex.org/W2136952590","https://openalex.org/W2140080674","https://openalex.org/W2147146929","https://openalex.org/W2148053845","https://openalex.org/W2148542244","https://openalex.org/W2161539186","https://openalex.org/W3021880308"],"related_works":["https://openalex.org/W1505787035","https://openalex.org/W1997145140","https://openalex.org/W1517687489","https://openalex.org/W2372170743","https://openalex.org/W2462936459","https://openalex.org/W1540992910","https://openalex.org/W2117014006","https://openalex.org/W2979086773","https://openalex.org/W1558545464","https://openalex.org/W2060252920"],"abstract_inverted_index":{"The":[0,74],"chip":[1],"maker?s":[2],"response":[3],"to":[4,90,102,107,141],"the":[5,17,35,42,61,85,108],"approaching":[6],"end":[7],"of":[8,72,79,87,99,114],"CPU":[9],"frequency":[10],"scaling":[11],"are":[12],"multicore":[13,118],"systems,":[14],"which":[15],"offer":[16],"same":[18],"programming":[19],"paradigm":[20],"as":[21,60,120],"traditional":[22],"shared":[23,69],"memory":[24,70],"platforms":[25],"but":[26],"have":[27],"different":[28],"performance":[29,46],"characteristics.":[30],"This":[31],"situation":[32],"considerably":[33],"increases":[34],"burden":[36],"on":[37],"library":[38],"developers":[39],"and":[40,54,94,98,138,148,151],"strengthens":[41],"case":[43],"for":[44,56,117,131],"automatic":[45],"tuning":[47],"frameworks":[48],"like":[49],"Spiral,":[50],"a":[51,68,80,100,111,127],"program":[52],"generator":[53],"optimizer":[55],"linear":[57],"transforms":[58],"such":[59],"discrete":[62],"Fourier":[63],"transform":[64,88],"(DFT).":[65],"We":[66],"present":[67],"extension":[71,75],"Spiral.":[73],"within":[76],"Spiral":[77],"consists":[78],"rewriting":[81],"system":[82],"that":[83,133],"manipulates":[84],"structure":[86],"algorithms":[89,115],"achieve":[91],"load":[92],"balancing":[93],"avoids":[95],"false":[96],"sharing,":[97],"backend":[101],"generate":[103],"multithreaded":[104],"code.":[105],"Application":[106],"DFT":[109,143],"produces":[110],"novel":[112],"class":[113],"suitable":[116],"systems":[119],"validated":[121],"by":[122],"experimental":[123],"results:":[124],"we":[125],"demonstrate":[126],"parallelization":[128],"speed-up":[129],"already":[130],"sizes":[132],"fit":[134],"into":[135],"L1":[136],"cache":[137],"compare":[139],"favorably":[140],"other":[142],"libraries":[144],"across":[145],"all":[146],"small":[147],"midsize":[149],"DFTs":[150],"considered":[152],"platforms.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}