{"id":"https://openalex.org/W4390188054","doi":"https://doi.org/10.1109/hpec58863.2023.10363536","title":"In-Place Multicore SIMD Fast Fourier Transforms","display_name":"In-Place Multicore SIMD Fast Fourier Transforms","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4390188054","doi":"https://doi.org/10.1109/hpec58863.2023.10363536"},"language":"en","primary_location":{"id":"doi:10.1109/hpec58863.2023.10363536","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/hpec58863.2023.10363536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-04240798v1/file/HPEC2023.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063862876","display_name":"Beno\u00eet Dupont de Dinechin","orcid":"https://orcid.org/0000-0002-3164-2765"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Beno\u00eet Dupont de Dinechin","raw_affiliation_strings":["Kalray SA,Montbonnot,France","Kalray SA, Montbonnot, France"],"affiliations":[{"raw_affiliation_string":"Kalray SA,Montbonnot,France","institution_ids":[]},{"raw_affiliation_string":"Kalray SA, Montbonnot, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047133169","display_name":"Julien Hasco\u00ebt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julien Hasco\u00ebt","raw_affiliation_strings":["Kalray SA,Montbonnot,France","Kalray SA, Montbonnot, France"],"affiliations":[{"raw_affiliation_string":"Kalray SA,Montbonnot,France","institution_ids":[]},{"raw_affiliation_string":"Kalray SA, Montbonnot, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034281565","display_name":"Or\u00e9gane Desrentes","orcid":null},"institutions":[{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Or\u00e8gane Desrentes","raw_affiliation_strings":["Kalray S.A. &#x0026; INSA Lyon (CITI),Montbonnot &#x0026; Villeurbanne,France"],"affiliations":[{"raw_affiliation_string":"Kalray S.A. &#x0026; INSA Lyon (CITI),Montbonnot &#x0026; Villeurbanne,France","institution_ids":["https://openalex.org/I48430043"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063862876"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3104,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55320778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9871000051498413,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8294135332107544},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.8263779282569885},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7935903072357178},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.781575620174408},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6874425411224365},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5582364201545715},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4652118980884552},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36339205503463745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294135332107544},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8263779282569885},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7935903072357178},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.781575620174408},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6874425411224365},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5582364201545715},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4652118980884552},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36339205503463745},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpec58863.2023.10363536","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/hpec58863.2023.10363536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04240798v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04240798","pdf_url":"https://inria.hal.science/hal-04240798v1/file/HPEC2023.pdf","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ieee-hpec.org/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04240798v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04240798","pdf_url":"https://inria.hal.science/hal-04240798v1/file/HPEC2023.pdf","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ieee-hpec.org/","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390188054.pdf","grobid_xml":"https://content.openalex.org/works/W4390188054.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W149408741","https://openalex.org/W372558526","https://openalex.org/W1566662854","https://openalex.org/W1988132189","https://openalex.org/W2004511788","https://openalex.org/W2050879237","https://openalex.org/W2052977106","https://openalex.org/W2068591469","https://openalex.org/W2069441027","https://openalex.org/W2074743336","https://openalex.org/W2077110374","https://openalex.org/W2127391977","https://openalex.org/W2161999391","https://openalex.org/W2977289290","https://openalex.org/W4205967631","https://openalex.org/W4308090450","https://openalex.org/W6862714336"],"related_works":["https://openalex.org/W2534771569","https://openalex.org/W2037547261","https://openalex.org/W4311812695","https://openalex.org/W1536455114","https://openalex.org/W1992352827","https://openalex.org/W2083992893","https://openalex.org/W1509422975","https://openalex.org/W2031026393","https://openalex.org/W2063611263","https://openalex.org/W2984139344"],"abstract_inverted_index":{"We":[0,79],"revisit":[1],"1D":[2],"Fast":[3],"Fourier":[4],"Transforms":[5],"(FFT)":[6],"implementation":[7],"approaches":[8],"in":[9],"the":[10,50,64,82,113,122],"context":[11],"of":[12,16,36,63,105],"compute":[13,117],"units":[14],"composed":[15],"multiple":[17],"cores":[18,72],"with":[19,53],"SIMD":[20,77,83],"ISA":[21],"extensions":[22],"and":[23,47,85,100],"sharing":[24],"a":[25],"multi-banked":[26,65],"local":[27,37,66],"memory.":[28],"A":[29,56],"main":[30],"constraint":[31],"is":[32,59,110],"to":[33,42,48,60,89],"spare":[34],"use":[35,43],"memory,":[38],"which":[39],"motivates":[40],"us":[41],"in-place":[44],"FFT":[45,92,128],"implementations":[46,93],"generate":[49],"twiddle":[51],"factors":[52],"trigonometric":[54],"recurrences.":[55],"key":[57],"objective":[58],"maximize":[61],"bandwidth":[62],"memory":[67],"system":[68],"by":[69],"ensuring":[70],"that":[71,94],"issue":[73],"maximum-width":[74],"aligned":[75],"non-temporal":[76],"accesses.":[78],"propose":[80],"combining":[81],"lane-slicing":[84],"sample":[86],"partitioning":[87],"techniques":[88],"derive":[90],"multicore":[91,127],"do":[95],"not":[96],"require":[97],"matrix":[98],"transpositions":[99],"only":[101],"involve":[102],"one":[103],"stage":[104],"bit-reverse":[106],"unscrambling.":[107],"This":[108],"approach":[109],"demonstrated":[111],"on":[112],"Kalray":[114],"MPPA3":[115],"processor":[116],"unit,":[118],"where":[119],"it":[120],"outperforms":[121],"classic":[123],"six-step":[124],"algorithm":[125],"for":[126],"implementation.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}
