{"id":"https://openalex.org/W2005168154","doi":"https://doi.org/10.1109/ispa.2012.96","title":"Towards the Dynamic Load Balancing on Heterogeneous Multi-GPU Systems","display_name":"Towards the Dynamic Load Balancing on Heterogeneous Multi-GPU Systems","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W2005168154","doi":"https://doi.org/10.1109/ispa.2012.96","mag":"2005168154"},"language":"en","primary_location":{"id":"doi:10.1109/ispa.2012.96","doi":"https://doi.org/10.1109/ispa.2012.96","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispa.2012.96","pdf_url":null,"source":{"id":"https://openalex.org/S7407088614","display_name":"IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 10th International Symposium on Parallel and Distributed Processing with Applications","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5039768232","display_name":"Alejandro Acosta","orcid":"https://orcid.org/0000-0001-5440-034X","observed_orcids":["https://orcid.org/0000-0001-5440-034X"]},"institutions":[{"id":"https://openalex.org/I158438070","display_name":"Universidad de La Laguna","ror":"https://ror.org/01r9z8p25","country_code":"ES","type":"education","lineage":["https://openalex.org/I158438070"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alejandro Acosta","raw_affiliation_strings":["Dept. Estadistica, I.O. y Comput., ETS Ing. Inf., La Laguna, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Estadistica, I.O. y Comput., ETS Ing. Inf., La Laguna, Spain","institution_ids":["https://openalex.org/I158438070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102992099","display_name":"Vicente Blanco","orcid":"https://orcid.org/0000-0003-1166-6310","observed_orcids":["https://orcid.org/0000-0003-1166-6310"]},"institutions":[{"id":"https://openalex.org/I158438070","display_name":"Universidad de La Laguna","ror":"https://ror.org/01r9z8p25","country_code":"ES","type":"education","lineage":["https://openalex.org/I158438070"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Vicente Blanco","raw_affiliation_strings":["Dept. Estadistica, I.O. y Comput., ETS Ing. Inf., La Laguna, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Estadistica, I.O. y Comput., ETS Ing. Inf., La Laguna, Spain","institution_ids":["https://openalex.org/I158438070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021916094","display_name":"Francisco Almeida","orcid":"https://orcid.org/0000-0002-1279-9636","observed_orcids":["https://orcid.org/0000-0002-1279-9636"]},"institutions":[{"id":"https://openalex.org/I158438070","display_name":"Universidad de La Laguna","ror":"https://ror.org/01r9z8p25","country_code":"ES","type":"education","lineage":["https://openalex.org/I158438070"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco Almeida","raw_affiliation_strings":["Dept. Estadistica, I.O. y Comput., ETS Ing. Inf., La Laguna, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Estadistica, I.O. y Comput., ETS Ing. Inf., La Laguna, Spain","institution_ids":["https://openalex.org/I158438070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I158438070"],"apc_list":null,"apc_paid":null,"fwci":2.1122,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87059969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"646","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9945999979972839,"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":0.9945999979972839,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.004600000102072954,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/dynamic-load-balancing","display_name":"dynamic load balancing","score":1.0},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.6740000247955322},{"id":"https://openalex.org/keywords/parallel-programming","display_name":"parallel programming","score":0.5220000147819519},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"matrix multiplication","score":0.6660000085830688},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"resource allocation","score":0.9810000061988831},{"id":"https://openalex.org/keywords/load-imbalance","display_name":"load imbalance","score":0.6890000104904175},{"id":"https://openalex.org/keywords/multicore-systems","display_name":"multi-core systems","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8570603132247925},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.7397300601005554},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.7016767263412476},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.625887930393219},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6027431488037109},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5724328756332397},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5053136944770813},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5032984614372253},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4839046895503998},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4702904224395752},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4605163335800171},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.44445645809173584},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.43944379687309265},{"id":"https://openalex.org/C2779370713","wikidata":"https://www.wikidata.org/wiki/Q357554","display_name":"Load management","level":2,"score":0.423356294631958},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41618895530700684},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22815701365470886},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14609378576278687},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.11089536547660828},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1096096932888031},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispa.2012.96","doi":"https://doi.org/10.1109/ispa.2012.96","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispa.2012.96","pdf_url":null,"source":{"id":"https://openalex.org/S7407088614","display_name":"IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 10th International Symposium on Parallel and Distributed Processing with Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1483880184","https://openalex.org/W1992851788","https://openalex.org/W2003094427","https://openalex.org/W2005900526","https://openalex.org/W2015935981","https://openalex.org/W2016279572","https://openalex.org/W2020988081","https://openalex.org/W2032238441","https://openalex.org/W2047656763","https://openalex.org/W2080592089","https://openalex.org/W2084115832","https://openalex.org/W2128022558","https://openalex.org/W2134373629","https://openalex.org/W2186110056","https://openalex.org/W2473914111","https://openalex.org/W4256269261"],"related_works":["https://openalex.org/W2064276071","https://openalex.org/W2084115832","https://openalex.org/W2473914111","https://openalex.org/W4256269261","https://openalex.org/W2103838950","https://openalex.org/W4413144829","https://openalex.org/W2791703188","https://openalex.org/W4313338955","https://openalex.org/W7065948506","https://openalex.org/W4221083541"],"abstract_inverted_index":{"The":[0,33,61,101,151],"advent":[1],"of":[2,10,25,29,63,98,154,166],"multicore":[3],"systems,":[4],"joined":[5],"to":[6,54,91,94,112,121,162],"the":[7,11,23,30,42,46,69,73,76,110,113,164],"potential":[8],"acceleration":[9],"graphics":[12],"processing":[13],"units,":[14],"alleviates":[15],"some":[16],"well":[17],"known":[18],"important":[19],"architectural":[20,37],"problems":[21,125],"at":[22,36,41],"expense":[24],"a":[26,58,82,95],"considerable":[27],"increment":[28],"programmability":[31],"wall.":[32],"heterogeneity,":[34],"both":[35],"and":[38,52,75,109,129,140,157],"programming":[39,47],"level":[40],"same":[43],"time,":[44],"raises":[45],"difficulties.":[48],"Adapting":[49],"existing":[50],"code":[51,65,74,90],"libraries":[53],"such":[55],"systems":[56,159],"is":[57,66,107],"fundamental":[59],"problem.":[60],"performance":[62],"this":[64],"affected":[67],"by":[68,104],"large":[70],"interdependence":[71],"between":[72],"parallel":[77,89],"architecture.":[78],"We":[79],"have":[80],"developed":[81],"dynamic":[83],"load":[84,123,168],"balancing":[85,169],"library":[86],"that":[87],"allows":[88],"be":[92],"adapted":[93],"wide":[96],"variety":[97],"heterogeneous":[99,130,146,158],"systems.":[100,150],"overhead":[102],"introduced":[103],"our":[105,167],"system":[106,117],"minimal":[108],"cost":[111],"programmer":[114],"negligible.":[115],"This":[116],"has":[118],"been":[119],"applied":[120],"solve":[122],"imbalance":[124],"appearing":[126],"in":[127,144,148],"homogeneous":[128],"multi-GPU":[131,149],"platforms.":[132],"As":[133],"case":[134],"studies,":[135],"we":[136],"consider":[137],"matrix":[138],"multiply":[139],"resource":[141],"allocation":[142],"problems,":[143],"different":[145],"scenarios":[147],"unbalanced":[152],"nature":[153],"these":[155],"algorithms":[156],"allowed":[160],"us":[161],"test":[163],"success":[165],"approach.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2016-06-24T00:00:00"}