{"id":"https://openalex.org/W4381389683","doi":"https://doi.org/10.1145/3589236.3589243","title":"LATOA: Load-Aware Task Offloading and Adoption in GPU","display_name":"LATOA: Load-Aware Task Offloading and Adoption in GPU","publication_year":2023,"publication_date":"2023-02-25","ids":{"openalex":"https://openalex.org/W4381389683","doi":"https://doi.org/10.1145/3589236.3589243"},"language":"en","primary_location":{"id":"doi:10.1145/3589236.3589243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589236.3589243","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589236.3589243","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589236.3589243","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062005982","display_name":"Hossein Bitalebi","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Hossein Bitalebi","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-7135-5130","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035117814","display_name":"Vahid Geraeinejad","orcid":"https://orcid.org/0000-0001-6996-608X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Vahid Geraeinejad","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-6996-608X","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043631824","display_name":"Farshad Safaei","orcid":"https://orcid.org/0000-0002-8546-3148"},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Farshad Safaei","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Shahid Beheshti University, Iran"],"raw_orcid":"https://orcid.org/0000-0002-8546-3148","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Shahid Beheshti University, Iran","institution_ids":["https://openalex.org/I48379061"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060584048","display_name":"Masoumeh Ebrahimi","orcid":"https://orcid.org/0000-0001-7877-6712"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Masoumeh Ebrahimi","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-7877-6712","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062005982"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07330082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"13"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9980000257492065,"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":0.8458157777786255},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.7872592210769653},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6850777268409729},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5820233821868896},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48777323961257935},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4795360565185547},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.4503980875015259},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4322056770324707},{"id":"https://openalex.org/keywords/stall","display_name":"Stall (fluid mechanics)","score":0.42937541007995605},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.4146757125854492},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3919737935066223},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.341346800327301},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2585628628730774},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.16589075326919556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458157777786255},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.7872592210769653},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6850777268409729},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5820233821868896},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48777323961257935},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4795360565185547},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.4503980875015259},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4322056770324707},{"id":"https://openalex.org/C5804382","wikidata":"https://www.wikidata.org/wiki/Q752034","display_name":"Stall (fluid mechanics)","level":2,"score":0.42937541007995605},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.4146757125854492},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3919737935066223},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.341346800327301},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2585628628730774},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.16589075326919556},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589236.3589243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589236.3589243","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589236.3589243","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589236.3589243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589236.3589243","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589236.3589243","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5299999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320939","display_name":"Swedish Foundation for International Cooperation in Research and Higher Education","ror":"https://ror.org/0561xc723"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381389683.pdf","grobid_xml":"https://content.openalex.org/works/W4381389683.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2080592089","https://openalex.org/W2167334577","https://openalex.org/W2273440736","https://openalex.org/W2412101011","https://openalex.org/W2517837804","https://openalex.org/W2794887017","https://openalex.org/W2795002137","https://openalex.org/W2884590322","https://openalex.org/W2900482429","https://openalex.org/W2949537427","https://openalex.org/W2952562588","https://openalex.org/W2991043486","https://openalex.org/W3043528907","https://openalex.org/W3128391996","https://openalex.org/W3128982134","https://openalex.org/W3161653145","https://openalex.org/W3173408461","https://openalex.org/W3216682567","https://openalex.org/W4206943884","https://openalex.org/W4221109973","https://openalex.org/W4236713805","https://openalex.org/W4280611505"],"related_works":["https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W1589409554","https://openalex.org/W2759038785","https://openalex.org/W3123876860","https://openalex.org/W3124172198","https://openalex.org/W2142633247","https://openalex.org/W2148394657","https://openalex.org/W2172232600","https://openalex.org/W2067473442"],"abstract_inverted_index":{"The":[0],"emerging":[1],"new":[2],"applications,":[3],"such":[4,32],"as":[5],"data":[6,97],"mining":[7],"and":[8,122,133,184,217,236,243],"graph":[9],"analysis,":[10],"demand":[11],"extra":[12],"processing":[13,66,80,164],"power":[14,237],"at":[15],"the":[16,29,42,78,90,99,138,154,191,199,208,219],"hardware":[17,230],"level.":[18],"Conventional":[19],"static":[20,143],"task":[21,146],"scheduling":[22,70,147],"is":[23,37,44,137],"no":[24],"longer":[25],"able":[26],"to":[27,46,73,89,110,144,190,194,198],"meet":[28],"requirements":[30],"of":[31,56,65,92,210],"complicated":[33],"applications.":[34],"This":[35],"inefficiency":[36],"a":[38,49,62,118],"major":[39],"concern":[40],"when":[41],"application":[43],"supposed":[45],"run":[47],"on":[48,149,203,213,222,239],"Graphics":[50],"Processing":[51],"Unit":[52],"(GPU),":[53],"where":[54],"millions":[55],"instructions":[57],"should":[58],"be":[59],"distributed":[60],"among":[61,77],"limited":[63],"number":[64,209],"cores.":[67,81],"A":[68],"non-optimal":[69],"strategy":[71],"leads":[72],"unfair":[74],"load":[75],"distribution":[76],"GPU\u2019s":[79],"Consequently,":[82],"while":[83],"busy":[84,108],"cores":[85,103,109,165,188],"are":[86,104,166,182],"stalled":[87],"due":[88],"lack":[91],"resources,":[93],"waiting":[94,106],"for":[95,107],"their":[96,112],"from":[98,142,153,186],"main":[100],"memory,":[101],"other":[102],"idle,":[105],"complete":[111],"tasks.":[113],"Our":[114],"study":[115,140],"introduces":[116],"LATOA,":[117,162],"Load-Aware":[119],"Task":[120],"Offloading":[121],"Adoption":[123],"method":[124],"that":[125],"tackles":[126],"this":[127],"problem":[128],"by":[129,215,224,241],"reducing":[130],"both":[131],"stall":[132,192,211],"idle":[134,200],"cycles.":[135],"LATOA":[136,206,232],"first":[139],"moving":[141],"dynamic":[145],"based":[148],"run-time":[150],"information":[151],"obtained":[152],"Miss":[155],"Status":[156],"Holding":[157],"Register":[158],"(MSHR)":[159],"tables.":[160],"In":[161,226],"all":[163],"dynamically":[167],"tagged":[168],"with":[169,178,228],"critical,":[170],"neutral,":[171],"or":[172],"relaxed":[173,195],"states.":[174],"Then,":[175],"irregular":[176],"warps":[177],"low":[179],"locality":[180],"properties":[181],"detected":[183],"offloaded":[185],"critical":[187],"(going":[189,197],"state)":[193],"ones":[196],"state).":[201],"Based":[202],"our":[204],"experiments,":[205],"reduces":[207],"cycles":[212],"average":[214,223,240],"24%":[216],"increases":[218],"neutral":[220],"states":[221],"38%.":[225],"addition,":[227],"negligible":[229],"overhead,":[231],"improves":[233],"system":[234],"performance":[235],"efficiency":[238],"26%":[242],"7%,":[244],"respectively.":[245]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}