{"id":"https://openalex.org/W4381327189","doi":"https://doi.org/10.1145/3577193.3593735","title":"OpenFFT: An Adaptive Tuning Framework for 3D FFT on ARM Multicore CPUs","display_name":"OpenFFT: An Adaptive Tuning Framework for 3D FFT on ARM Multicore CPUs","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4381327189","doi":"https://doi.org/10.1145/3577193.3593735"},"language":"en","primary_location":{"id":"doi:10.1145/3577193.3593735","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577193.3593735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-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/A5060305663","display_name":"Tun Chen","orcid":"https://orcid.org/0000-0003-3459-7960"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tun Chen","raw_affiliation_strings":["High Performance Computer Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China","High Performance Computer Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3459-7960","affiliations":[{"raw_affiliation_string":"High Performance Computer Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"High Performance Computer Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101816350","display_name":"Haipeng Jia","orcid":"https://orcid.org/0000-0002-9855-5367"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Jia","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9855-5367","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016255357","display_name":"Yunquan Zhang","orcid":"https://orcid.org/0000-0001-7520-9640"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunquan Zhang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7520-9640","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377529","display_name":"Kun Li","orcid":"https://orcid.org/0000-0002-1013-1325"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1013-1325","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380123","display_name":"Zhihao Li","orcid":"https://orcid.org/0000-0002-6149-0627"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Li","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6149-0627","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103164456","display_name":"Xiang Zhao","orcid":"https://orcid.org/0009-0003-2432-6507"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Zhao","raw_affiliation_strings":["Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0003-2432-6507","affiliations":[{"raw_affiliation_string":"Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639385","display_name":"Jianyu Yao","orcid":"https://orcid.org/0009-0003-2889-4499"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Yao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-2889-4499","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028785761","display_name":"Chendi Li","orcid":"https://orcid.org/0009-0000-2610-042X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chendi Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2610-042X","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1498,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75543726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"398","last_page":"409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.994700014591217,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8726192712783813},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8056501150131226},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.6597865223884583},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.597524881362915},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5338211059570312},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5216003656387329},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4384418725967407},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.42085132002830505},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2707008123397827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8726192712783813},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8056501150131226},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.6597865223884583},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.597524881362915},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5338211059570312},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5216003656387329},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4384418725967407},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.42085132002830505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2707008123397827},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577193.3593735","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577193.3593735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","score":0.5,"id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1966904279","https://openalex.org/W1985765205","https://openalex.org/W2011191879","https://openalex.org/W2022028092","https://openalex.org/W2030799875","https://openalex.org/W2045836768","https://openalex.org/W2061171222","https://openalex.org/W2078095679","https://openalex.org/W2102182691","https://openalex.org/W2106805276","https://openalex.org/W2134572726","https://openalex.org/W2135031801","https://openalex.org/W2135736783","https://openalex.org/W2162323496","https://openalex.org/W2345567770","https://openalex.org/W2546716216","https://openalex.org/W2885155955","https://openalex.org/W2979071126","https://openalex.org/W3010781441","https://openalex.org/W3103952756","https://openalex.org/W3166510811","https://openalex.org/W4236989128","https://openalex.org/W4252735936","https://openalex.org/W6658315997","https://openalex.org/W6670077436"],"related_works":["https://openalex.org/W2363677236","https://openalex.org/W2007964072","https://openalex.org/W2078036665","https://openalex.org/W2001031944","https://openalex.org/W778337757","https://openalex.org/W4205439893","https://openalex.org/W2102140193","https://openalex.org/W2085237598","https://openalex.org/W2006835125","https://openalex.org/W2159870643"],"abstract_inverted_index":{"The":[0],"sophisticated":[1],"hierarchy":[2,139],"and":[3,24,107,140,163],"shared":[4],"characteristics":[5,136],"of":[6,18,81,122,125,137,161],"cache":[7,138],"in":[8,22],"multicore":[9],"CPU":[10],"architectures":[11],"bring":[12],"challenges":[13],"to":[14,54,103,117,143],"the":[15,42,46,78,85,97,119,135,158],"performance":[16,156],"improvement":[17],"fundamental":[19],"algorithms,":[20],"especially":[21,60],"implementing":[23],"optimizing":[25],"3D":[26,28,69,82],"FFT.":[27],"FFT":[29,70,83],"is":[30,52],"a":[31,68,153],"memory-bounded":[32],"algorithm":[33,99,114,116],"that":[34,149],"contains":[35],"many":[36],"highly":[37],"discretized":[38],"memory":[39,57,79,120],"accesses.":[40],"With":[41],"working":[43],"set":[44],"scaling,":[45],"data":[47,63,105],"locality":[48,106],"becomes":[49],"poor,":[50],"which":[51],"prone":[53],"cause":[55],"serious":[56],"access":[58,80,121],"overhead,":[59],"for":[61,100],"high-dimensional":[62,101],"transposition.":[64],"This":[65,75],"paper":[66],"proposes":[67],"optimization":[71],"framework":[72,76],"named":[73],"OpenFFT.":[74],"optimizes":[77],"by":[84,133],"following":[86],"methods,":[87],"including":[88],"1)":[89],"A":[90,129],"novel":[91],"tiling":[92],"algorithm,":[93],"Z-OpenFFT,":[94],"based":[95],"on":[96,165],"column-order":[98],"vectorization":[102],"improve":[104],"eliminate":[108],"transposition;":[109],"2)":[110],"An":[111],"efficient":[112],"search":[113],"Section-cache-aware":[115],"optimize":[118],"butterfly":[123],"network":[124],"1D":[126],"FFT;":[127],"3)":[128],"multi-thread":[130],"allocation":[131],"model":[132],"analyzing":[134],"task":[141],"size":[142],"allocate":[144],"threads":[145],"adaptively.":[146],"Experiments":[147],"demonstrate":[148],"OpenFFT":[150],"could":[151],"obtain":[152],"more":[154],"competitive":[155],"than":[157],"best":[159],"configuration":[160],"FFTW":[162],"ARMPL":[164],"ARM":[166],"CPUs.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}
