{"id":"https://openalex.org/W2996645684","doi":"https://doi.org/10.1145/3368474.3368488","title":"FFTE on SVE","display_name":"FFTE on SVE","publication_year":2019,"publication_date":"2019-12-17","ids":{"openalex":"https://openalex.org/W2996645684","doi":"https://doi.org/10.1145/3368474.3368488","mag":"2996645684"},"language":"en","primary_location":{"id":"doi:10.1145/3368474.3368488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368474.3368488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","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/A5100710410","display_name":"Daisuke Takahashi","orcid":"https://orcid.org/0000-0003-1357-5770"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Takahashi","raw_affiliation_strings":["Center for Computational Sciences, University of Tsukuba Tsukuba, Ibaraki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Sciences, University of Tsukuba Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","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":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"114","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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":0.9980000257492065,"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":0.9078336358070374},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.8999894857406616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7588128447532654},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7374368906021118},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7199073433876038},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5312734842300415},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5221008062362671},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.4445541799068451},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3850492238998413},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2811152935028076},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23365291953086853},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08091023564338684}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.9078336358070374},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.8999894857406616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588128447532654},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7374368906021118},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7199073433876038},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5312734842300415},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5221008062362671},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.4445541799068451},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3850492238998413},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2811152935028076},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23365291953086853},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08091023564338684},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3368474.3368488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368474.3368488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W99177659","https://openalex.org/W1534960753","https://openalex.org/W1542357320","https://openalex.org/W1990860452","https://openalex.org/W2018641575","https://openalex.org/W2043899910","https://openalex.org/W2045810654","https://openalex.org/W2061171222","https://openalex.org/W2102182691","https://openalex.org/W2106445473","https://openalex.org/W2134572726","https://openalex.org/W2136952590","https://openalex.org/W2140080674","https://openalex.org/W2168353136","https://openalex.org/W2613264175","https://openalex.org/W2727737523","https://openalex.org/W2898200251","https://openalex.org/W2938324068","https://openalex.org/W3123542955","https://openalex.org/W4244941945"],"related_works":["https://openalex.org/W2979513934","https://openalex.org/W2351155539","https://openalex.org/W1968359082","https://openalex.org/W1990169291","https://openalex.org/W2996645684","https://openalex.org/W2049509090","https://openalex.org/W2013156670","https://openalex.org/W2098868092","https://openalex.org/W2357128959","https://openalex.org/W2886331427"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"an":[5,28],"implementation":[6],"of":[7,49,58,87],"the":[8,14,41,46,68],"fast":[9],"Fourier":[10],"transform":[11],"(FFT)":[12],"targeting":[13],"ARM":[15,69],"Scalable":[16],"Vector":[17],"Extension":[18],"(SVE).":[19],"We":[20,43],"performed":[21],"automatic":[22],"vectorization":[23,30,48],"via":[24],"a":[25],"compiler":[26,70],"and":[27,39,92],"explicit":[29,47],"through":[31],"code":[32,52],"generation":[33],"by":[34],"SPIRAL":[35,50],"for":[36],"FFT":[37,72,85,100],"kernels,":[38],"compared":[40],"performance.":[42],"show":[44],"that":[45],"generated":[51],"improves":[53],"performance":[54],"significantly.":[55],"Performance":[56],"results":[57],"FFTs":[59],"on":[60],"RIKEN's":[61],"Fugaku":[62],"processor":[63],"simulator":[64],"are":[65,78],"reported.":[66],"With":[67],"SPIRAL-generated":[71,99],"kernels":[73,86,101],"written":[74,89,102],"in":[75,90,103],"SVE":[76],"intrinsic":[77],"up":[79,93],"to":[80,94],"3.16":[81],"times":[82,96],"faster":[83,97],"than":[84,98],"FFTE":[88],"Fortran":[91],"5.62":[95],"C.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-12-26T00:00:00"}
