{"id":"https://openalex.org/W4220822006","doi":"https://doi.org/10.1145/3529113.3529122","title":"Evaluating FFT-based Algorithms for Strided Convolutions on ARMv8 Architectures?","display_name":"Evaluating FFT-based Algorithms for Strided Convolutions on ARMv8 Architectures?","publication_year":2022,"publication_date":"2022-03-22","ids":{"openalex":"https://openalex.org/W4220822006","doi":"https://doi.org/10.1145/3529113.3529122"},"language":"en","primary_location":{"id":"doi:10.1145/3529113.3529122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529113.3529122","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-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/A5013047230","display_name":"Xiandong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiandong Huang","raw_affiliation_strings":["National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101913669","display_name":"Qinglin Wang","orcid":"https://orcid.org/0000-0002-8286-6566"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglin Wang","raw_affiliation_strings":["National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025604456","display_name":"Shuyu Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuyu Lu","raw_affiliation_strings":["University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004057249","display_name":"Ruochen Hao","orcid":"https://orcid.org/0000-0002-1162-1879"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruochen Hao","raw_affiliation_strings":["National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066267776","display_name":"Songzhu Mei","orcid":"https://orcid.org/0000-0002-4926-5953"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songzhu Mei","raw_affiliation_strings":["National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454211","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-3745-7541"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5013047230"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.6045,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65677066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"49","issue":"3","first_page":"28","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7750140428543091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7709122896194458},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6461894512176514},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5748847723007202},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5743796229362488},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5736324787139893},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5711644887924194},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5323657989501953},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.45669040083885193},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4501025676727295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19109803438186646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16365393996238708}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.7750140428543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709122896194458},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6461894512176514},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5748847723007202},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5743796229362488},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5736324787139893},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5711644887924194},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5323657989501953},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.45669040083885193},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4501025676727295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19109803438186646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16365393996238708},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3529113.3529122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529113.3529122","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2946383579","https://openalex.org/W3154028478","https://openalex.org/W3203564148"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2002978035","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W4327521644"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4],"been":[5],"widely":[6],"adopted":[7],"in":[8,136,168],"all":[9],"kinds":[10],"of":[11,16,20,56,84,113],"artificial":[12],"intelligence":[13],"applications.":[14],"Most":[15],"the":[17,32,79,85,97,100,124,129,133,152,165,173],"computational":[18],"overhead":[19,33],"CNNs":[21,170],"is":[22,34],"mainly":[23],"spent":[24],"on":[25,75,88,104],"convolutions.":[26,39,77],"An":[27],"effective":[28],"approach":[29],"to":[30,49],"reducing":[31],"FFT-based":[35,42,72],"fast":[36,43,73],"algorithms":[37,74],"for":[38,70],"However,":[40],"current":[41],"implementations":[44,83,98,103],"cannot":[45],"be":[46],"directly":[47],"applied":[48],"strided":[50,76],"convolutions":[51,112],"with":[52,111,164],"a":[53],"stride":[54],"size":[55],"greater":[57],"than":[58,148],"1.":[59],"In":[60],"this":[61,105],"paper,":[62],"we":[63,95],"first":[64],"introduce":[65],"rearrangement-":[66],"and":[67,116,119,139,156],"sampling-based":[68,130],"methods":[69,87,142],"applying":[71],"Then,":[78],"highly":[80],"optimized":[81],"parallel":[82],"two":[86,101,141],"ARMv8-based":[89],"many-core":[90],"CPU":[91],"are":[92,159],"presented.":[93],"Lastly,":[94],"benchmark":[96],"against":[99],"GEMM-based":[102],"ARMv8":[106],"CPU.":[107],"Our":[108],"experimental":[109,162],"results":[110,163],"different":[114],"kernel,":[115,153],"feature":[117,154],"maps,":[118],"batch":[120,157],"sizes":[121,158],"show":[122],"that":[123],"rearrangementbased":[125],"method":[126],"generally":[127],"exceed":[128],"one":[131],"under":[132],"same":[134],"optimizations":[135],"most":[137],"cases,":[138],"these":[140],"can":[143],"get":[144],"much":[145],"better":[146],"performance":[147],"GEMMbased":[149],"ones":[150],"when":[151],"maps":[155],"large.":[160],"The":[161],"convolutional":[166],"layers":[167],"popular":[169],"further":[171],"demonstrate":[172],"conclusion":[174],"above.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}