{"id":"https://openalex.org/W3202574579","doi":"https://doi.org/10.1145/3472456.3472474","title":"FastPSO: Towards Efficient Swarm Intelligence Algorithm on GPUs","display_name":"FastPSO: Towards Efficient Swarm Intelligence Algorithm on GPUs","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3202574579","doi":"https://doi.org/10.1145/3472456.3472474","mag":"3202574579"},"language":"en","primary_location":{"id":"doi:10.1145/3472456.3472474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3472474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","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/A5019116334","display_name":"Hanfeng Liu","orcid":"https://orcid.org/0009-0003-7338-552X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hanfeng Liu","raw_affiliation_strings":["DMAI ltd, China"],"affiliations":[{"raw_affiliation_string":"DMAI ltd, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013127195","display_name":"Zeyi Wen","orcid":"https://orcid.org/0000-0003-3370-6053"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zeyi Wen","raw_affiliation_strings":["The University of Western Australia"],"affiliations":[{"raw_affiliation_string":"The University of Western Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053432286","display_name":"Wei Cai","orcid":"https://orcid.org/0000-0002-4658-0034"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Cai","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019116334"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63625833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9980000257492065,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9959999918937683,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9879999756813049,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7831341624259949},{"id":"https://openalex.org/keywords/swarm-intelligence","display_name":"Swarm intelligence","score":0.7072242498397827},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.5828337669372559},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4636247158050537},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3962985873222351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27432671189308167},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.18206152319908142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831341624259949},{"id":"https://openalex.org/C119487961","wikidata":"https://www.wikidata.org/wiki/Q863960","display_name":"Swarm intelligence","level":3,"score":0.7072242498397827},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.5828337669372559},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4636247158050537},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3962985873222351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27432671189308167},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.18206152319908142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3472456.3472474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3472474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-161517","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-161517","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W329627939","https://openalex.org/W1478687540","https://openalex.org/W1525847951","https://openalex.org/W1573676079","https://openalex.org/W1637395725","https://openalex.org/W1769447825","https://openalex.org/W1979566015","https://openalex.org/W1992851788","https://openalex.org/W1999077811","https://openalex.org/W2006841864","https://openalex.org/W2019884884","https://openalex.org/W2030640142","https://openalex.org/W2038456806","https://openalex.org/W2043218896","https://openalex.org/W2092675140","https://openalex.org/W2101234009","https://openalex.org/W2110365363","https://openalex.org/W2152195021","https://openalex.org/W2154950655","https://openalex.org/W2335884387","https://openalex.org/W2342949225","https://openalex.org/W2518314348","https://openalex.org/W2581945606","https://openalex.org/W2602337361","https://openalex.org/W2783515600","https://openalex.org/W2912265134","https://openalex.org/W2941681018","https://openalex.org/W2947137917","https://openalex.org/W2951402759","https://openalex.org/W2995694143","https://openalex.org/W3026711567","https://openalex.org/W3113960897","https://openalex.org/W4255788608","https://openalex.org/W4292083457","https://openalex.org/W6758229760"],"related_works":["https://openalex.org/W4308079021","https://openalex.org/W1527337688","https://openalex.org/W2399799070","https://openalex.org/W2048054807","https://openalex.org/W2746377055","https://openalex.org/W4386001959","https://openalex.org/W2594296178","https://openalex.org/W4304182880","https://openalex.org/W3089846858","https://openalex.org/W2159541481"],"abstract_inverted_index":{"Particle":[0],"Swarm":[1],"Optimization":[2],"(PSO)":[3],"has":[4],"been":[5],"widely":[6],"used":[7],"in":[8,48,99],"various":[9],"optimization":[10,25,75,185,229],"tasks":[11],"(e.g.,":[12],"neural":[13],"architecture":[14],"search":[15],"and":[16,29,106,168,213],"autonomous":[17],"vehicle":[18],"navigation),":[19],"because":[20],"it":[21],"can":[22],"solve":[23],"non-convex":[24],"problems":[26],"with":[27,63,149],"simplicity":[28],"efficacy.":[30],"However,":[31],"the":[32,60,67,73,86,96,103,135,189,203,215],"PSO":[33,61,74,206],"algorithm":[34,62,93,193],"is":[35,139],"often":[36],"time-consuming":[37],"to":[38,58,94,117,128,145,159,173,187,221],"use,":[39],"especially":[40],"for":[41],"high-dimensional":[42],"problems,":[43],"which":[44],"hinders":[45],"its":[46],"applicability":[47],"time-critical":[49],"applications.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,70,88,110],"propose":[55,111],"novel":[56,115],"techniques":[57,116,144],"accelerate":[59],"GPUs.":[64],"To":[65],"mitigate":[66],"efficiency":[68,190],"bottleneck,":[69],"formally":[71],"model":[72],"as":[76],"a":[77,112,171],"process":[78],"of":[79,114,137,164,191,211],"element-wise":[80,97],"operations":[81,98],"on":[82,85,183],"matrices.":[83],"Based":[84],"modeling,":[87],"develop":[89],"an":[90],"efficient":[91],"GPU":[92,124,156],"perform":[95],"massively":[100],"parallel":[101,143],"using":[102],"tensor":[104],"cores":[105],"shared":[107],"memory.":[108],"Moreover,":[109],"series":[113],"improve":[118],"our":[119,192],"proposed":[120],"algorithm,":[121],"including":[122],"(i)":[123],"resource-aware":[125],"thread":[126],"creation":[127],"prevent":[129],"creating":[130],"too":[131],"many":[132],"threads":[133],"when":[134],"number":[136,152],"particles/dimensions":[138],"large;":[140],"(ii)":[141],"designing":[142],"initialize":[146],"swarm":[147,161,176],"particles":[148],"fast":[150],"random":[151],"generation;":[153],"(iii)":[154],"exploiting":[155],"memory":[157,167],"caching":[158],"manage":[160],"information":[162],"instead":[163],"allocating":[165],"new":[166],"(iv)":[169],"developing":[170],"schema":[172],"support":[174],"customized":[175],"evaluation":[177],"functions.":[178],"We":[179],"conduct":[180],"extensive":[181],"experiments":[182],"four":[184],"applications":[186],"study":[188],"called":[194],"\u201cFastPSO\u201d.":[195],"Experimental":[196],"results":[197],"show":[198],"that":[199],"FastPSO":[200],"consistently":[201],"outperforms":[202],"existing":[204,216],"CPU-based":[205],"libraries":[207],"by":[208,219],"two":[209],"orders":[210],"magnitude,":[212],"transcends":[214],"GPU-based":[217],"implementation":[218],"5":[220],"7":[222],"times,":[223],"while":[224],"achieving":[225],"better":[226],"or":[227],"competitive":[228],"results.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
