{"id":"https://openalex.org/W2086105136","doi":"https://doi.org/10.1109/hpcsim.2012.6266966","title":"Algorithmic strategies for optimizing the parallel reduction primitive in CUDA","display_name":"Algorithmic strategies for optimizing the parallel reduction primitive in CUDA","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W2086105136","doi":"https://doi.org/10.1109/hpcsim.2012.6266966","mag":"2086105136"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2012.6266966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2012.6266966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on High Performance Computing & Simulation (HPCS)","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/A5035865191","display_name":"Pedro Mart\u00edn","orcid":"https://orcid.org/0000-0003-4242-0145"},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pedro J. Martin","raw_affiliation_strings":["Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n, Universidad Complutense de Madrid, Madrid, Spain","Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n; Universidad Complutense de Madrid; Madrid Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n, Universidad Complutense de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]},{"raw_affiliation_string":"Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n; Universidad Complutense de Madrid; Madrid Spain","institution_ids":["https://openalex.org/I121748325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023640635","display_name":"Luis F. Ayuso","orcid":null},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis F. Ayuso","raw_affiliation_strings":["Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n, Universidad Complutense de Madrid, Madrid, Spain","Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n; Universidad Complutense de Madrid; Madrid Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n, Universidad Complutense de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]},{"raw_affiliation_string":"Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n; Universidad Complutense de Madrid; Madrid Spain","institution_ids":["https://openalex.org/I121748325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113687680","display_name":"Roberto Torres","orcid":null},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Roberto Torres","raw_affiliation_strings":["Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n, Universidad Complutense de Madrid, Madrid, Spain","Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n; Universidad Complutense de Madrid; Madrid Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n, Universidad Complutense de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]},{"raw_affiliation_string":"Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n; Universidad Complutense de Madrid; Madrid Spain","institution_ids":["https://openalex.org/I121748325"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009577466","display_name":"Antonio Gavilanes","orcid":null},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Gavilanes","raw_affiliation_strings":["Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n, Universidad Complutense de Madrid, Madrid, Spain","Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n; Universidad Complutense de Madrid; Madrid Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n, Universidad Complutense de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I121748325"]},{"raw_affiliation_string":"Departamento de Sistemas Inform\u00e1ticos y Computaci\u00f3n; Universidad Complutense de Madrid; Madrid Spain","institution_ids":["https://openalex.org/I121748325"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121748325"],"apc_list":null,"apc_paid":null,"fwci":1.3239,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.79255421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"511","last_page":"519"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9980000257492065,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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":0.8692436814308167},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7543826103210449},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6584981679916382},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6275873184204102},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5614343881607056},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4596417248249054},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4532817006111145},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.419332355260849},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4118143320083618},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3843652307987213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8692436814308167},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7543826103210449},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6584981679916382},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6275873184204102},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5614343881607056},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4596417248249054},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4532817006111145},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.419332355260849},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4118143320083618},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3843652307987213},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpcsim.2012.6266966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2012.6266966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.569.3210","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.569.3210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csd.uwo.ca/~moreno/CS433-CS9624/Resources/Algorithmic_strategies_for_optimizing_the_parallel_reduction_primitive_in_CUDA.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1227119782","https://openalex.org/W1487977379","https://openalex.org/W1595783387","https://openalex.org/W1967321130","https://openalex.org/W2019708326","https://openalex.org/W2049875313","https://openalex.org/W2067313328","https://openalex.org/W2112708371","https://openalex.org/W2113841249","https://openalex.org/W2119547137","https://openalex.org/W2124007994","https://openalex.org/W2126212855","https://openalex.org/W2130931788","https://openalex.org/W2153226019","https://openalex.org/W3147336131","https://openalex.org/W4214596219","https://openalex.org/W6628145964","https://openalex.org/W6678107477"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W2032508741","https://openalex.org/W2363538625","https://openalex.org/W4297775710","https://openalex.org/W1937514268"],"abstract_inverted_index":{"Many":[0],"general-purpose":[1],"applications":[2],"exploit":[3],"Graphics":[4],"Processing":[5],"Units":[6],"(GPUs)":[7],"by":[8],"executing":[9],"a":[10,30,75,79,83,98],"set":[11],"of":[12,36,43,100,120,156,166,190],"well-known":[13],"dataparallel":[14],"primitives.":[15],"Those":[16],"primitives":[17],"are":[18,133,209],"usually":[19],"invoked":[20],"from":[21],"the":[22,34,37,41,59,69,136,153,157,162,180,188,193],"host":[23],"many":[24],"times,":[25],"so":[26],"their":[27,49],"throughput":[28,144,184],"has":[29],"great":[31],"impact":[32],"on":[33,51,67,96,124,187],"performance":[35,103],"overall":[38],"system.":[39],"Thus,":[40,110],"study":[42,119],"novel":[44],"algorithmic":[45,130],"strategies":[46],"to":[47,58,115,152,196],"optimize":[48],"implementation":[50],"current":[52],"devices":[53],"is":[54,114,164,174],"an":[55,117],"interesting":[56],"topic":[57],"GPU":[60],"community.":[61],"In":[62,170],"this":[63,150,171],"paper":[64],"we":[65,127,148],"focus":[66],"optimizing":[68],"reduction":[70,122],"primitive,":[71,158],"which":[72,159,177],"merely":[73],"reduces":[74],"data":[76],"sequence":[77],"into":[78,135],"single":[80],"value":[81],"using":[82],"binary":[84],"associative":[85],"operator.":[86],"Although":[87],"tree-based":[88,199],"and":[89,213],"sequential-based":[90,140],"algorithms":[91,123,200],"have":[92],"been":[93,106],"already":[94],"implemented":[95],"GPUs,":[97],"comparison":[99],"both":[101],"algorithm":[102,178],"had":[104],"not":[105,175],"carried":[107],"out":[108],"yet.":[109],"our":[111,197],"first":[112],"contribution":[113],"present":[116],"experimental":[118],"state-of-the-art":[121],"CUDA.":[125],"Next":[126],"introduce":[128],"two":[129],"optimizations":[131],"that":[132],"integrated":[134],"fastest":[137],"solution":[138],"(a":[139],"algorithm),":[141],"improving":[142],"its":[143],"even":[145],"more.":[146],"Finally,":[147],"replicate":[149],"methodology":[151],"segmented":[154],"version":[155],"applies":[160],"when":[161],"input":[163],"composed":[165],"several":[167],"independent":[168],"segments.":[169],"case,":[172],"it":[173],"clear":[176],"exhibits":[179],"best":[181],"performance,":[182],"since":[183],"deeply":[185],"depends":[186],"distribution":[189],"segments":[191],"along":[192],"input.":[194],"According":[195],"results,":[198],"run":[201],"faster":[202],"for":[203,211],"small":[204],"segments,":[205],"while":[206],"sequential":[207],"methods":[208],"better":[210],"medium":[212],"large":[214],"ones.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}