{"id":"https://openalex.org/W2555931724","doi":"https://doi.org/10.1109/tpds.2016.2631166","title":"A Dynamic Approach for Workload Partitioning on GPU Architectures","display_name":"A Dynamic Approach for Workload Partitioning on GPU Architectures","publication_year":2016,"publication_date":"2016-11-22","ids":{"openalex":"https://openalex.org/W2555931724","doi":"https://doi.org/10.1109/tpds.2016.2631166","mag":"2555931724"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2631166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2631166","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5053217543","display_name":"Federico Busato","orcid":null},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Federico Busato","raw_affiliation_strings":["Department of Computer Science, University of Verona, VR, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Verona, VR, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088231786","display_name":"Nicola Bombieri","orcid":"https://orcid.org/0000-0003-3256-5885"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Bombieri","raw_affiliation_strings":["Department of Computer Science, University of Verona, VR, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Verona, VR, Italy","institution_ids":["https://openalex.org/I119439378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053217543"],"corresponding_institution_ids":["https://openalex.org/I119439378"],"apc_list":null,"apc_paid":null,"fwci":1.892,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85715629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"28","issue":"6","first_page":"1535","last_page":"1549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9110930562019348},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.7585256099700928},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7346137762069702},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6198508739471436},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5266116857528687},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4525430202484131},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.44095301628112793},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42393097281455994},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41625383496284485},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3393331468105316},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1556943655014038},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09276556968688965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9110930562019348},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7585256099700928},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7346137762069702},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6198508739471436},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5266116857528687},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4525430202484131},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.44095301628112793},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42393097281455994},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41625383496284485},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3393331468105316},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1556943655014038},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09276556968688965}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2016.2631166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2631166","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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":27,"referenced_works":["https://openalex.org/W116067572","https://openalex.org/W1504291959","https://openalex.org/W1506342804","https://openalex.org/W1770249075","https://openalex.org/W1893178273","https://openalex.org/W1967321130","https://openalex.org/W1985291160","https://openalex.org/W2019708326","https://openalex.org/W2022219663","https://openalex.org/W2022541337","https://openalex.org/W2035080386","https://openalex.org/W2049875313","https://openalex.org/W2059966434","https://openalex.org/W2085248745","https://openalex.org/W2087977509","https://openalex.org/W2107173440","https://openalex.org/W2109473404","https://openalex.org/W2126739950","https://openalex.org/W2128853364","https://openalex.org/W2165633563","https://openalex.org/W2208875625","https://openalex.org/W2502734103","https://openalex.org/W2739266613","https://openalex.org/W3147336131","https://openalex.org/W4246219036","https://openalex.org/W6604758536","https://openalex.org/W6962870248"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Workload":[0],"partitioning":[1,116,140],"and":[2,117,141,169,180,184,196,205,210],"the":[3,31,36,45,50,86,91,98,129,139,152,157,161,171,177,188,191],"subsequent":[4],"work":[5,118],"item-to-thread":[6,119],"mapping":[7,120,142],"are":[8],"key":[9],"aspects":[10],"to":[11,24,35,79,128,193,207],"face":[12],"when":[13,71,102,209],"implementing":[14],"any":[15],"efficient":[16,111],"GPU":[17,153,199],"application.":[18],"Different":[19],"techniques":[20,186],"have":[21],"been":[22,145],"proposed":[23,178],"deal":[25],"with":[26,82,126,156],"such":[27],"issues,":[28],"ranging":[29],"from":[30],"computationally":[32],"simplest":[33],"static":[34],"most":[37],"complex":[38],"dynamic":[39,58,92,112,131],"ones.":[40],"Each":[41],"of":[42,65,151,159,190],"them":[43,66],"finds":[44],"best":[46,214],"use":[47],"depending":[48],"on":[49,104],"workload":[51,115],"characteristics":[52,155],"(static":[53],"for":[54,59,114],"more":[55],"regular":[56,105],"workloads,":[57],"irregular":[60,83],"workloads).":[61],"Nevertheless,":[62],"no":[63],"one":[64],"provides":[67],"a":[68],"sound":[69],"tradeoff":[70],"applied":[72],"in":[73,133],"both":[74],"cases.":[75],"Static":[76],"approaches":[77,95,132],"lead":[78],"load":[80],"unbalancing":[81],"problems,":[84],"while":[85],"computational":[87,163],"overhead":[88],"introduced":[89],"by":[90,147,175],"or":[93],"semi-dynamic":[94,185],"often":[96],"worsens":[97],"overall":[99],"application":[100],"performance":[101],"run":[103],"problems.":[106],"This":[107],"article":[108,136,166],"presents":[109],"an":[110],"technique":[113,213],"whose":[121],"complexity":[122],"is":[123],"significantly":[124],"reduced":[125],"respect":[127],"other":[130],"literature.":[134],"The":[135,165],"shows":[137],"how":[138,211],"algorithm":[143],"has":[144],"implemented":[146],"fully":[148],"taking":[149],"advantage":[150],"device":[154],"aim":[158],"minimizing":[160],"involved":[162],"overhead.":[164],"shows,":[167],"compares,":[168],"analyses":[170],"experimental":[172],"results":[173],"obtained":[174],"applying":[176],"approach":[179],"several":[181],"static,":[182],"dynamic,":[183],"at":[187],"state":[189],"art":[192],"different":[194,198],"benchmarks":[195],"over":[197],"technologies":[200],"(i.e.,":[201],"NVIDIA":[202],"Fermi,":[203],"Kepler,":[204],"Maxwell)":[206],"understand":[208],"each":[212],"applies.":[215]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}