{"id":"https://openalex.org/W4414197846","doi":"https://doi.org/10.1109/dac63849.2025.11133076","title":"VISTA: Optimizing GPU Scheduling through Versatile Locality-Aware Data Sharing","display_name":"VISTA: Optimizing GPU Scheduling through Versatile Locality-Aware Data Sharing","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414197846","doi":"https://doi.org/10.1109/dac63849.2025.11133076"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11133076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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/A5019048190","display_name":"Hajar Falahati","orcid":"https://orcid.org/0000-0001-8375-3339"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Hajar Falahati","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC),Barcelona,Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC),Barcelona,Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053374807","display_name":"Negin Mahani","orcid":"https://orcid.org/0000-0001-5232-3539"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Negin Mahani","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC),Barcelona,Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC),Barcelona,Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084390427","display_name":"Adri\u00e1n Cristal","orcid":"https://orcid.org/0000-0003-1277-9296"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adrian Cristal","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC),Barcelona,Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC),Barcelona,Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075162875","display_name":"Osman \u00dcnsal","orcid":"https://orcid.org/0000-0002-0544-9697"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Osman Unsal","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC),Barcelona,Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC),Barcelona,Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019048190"],"corresponding_institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2998954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9695000052452087,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9695000052452087,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9387999773025513,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9254999756813049,"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/thread","display_name":"Thread (computing)","score":0.5924000144004822},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5784000158309937},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5498999953269958},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.448199987411499},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.43779999017715454},{"id":"https://openalex.org/keywords/gang-scheduling","display_name":"Gang scheduling","score":0.4065999984741211},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.39309999346733093},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.3889999985694885},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.38609999418258667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.883899986743927},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5659999847412109},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4846999943256378},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C201515029","wikidata":"https://www.wikidata.org/wiki/Q5520966","display_name":"Gang scheduling","level":5,"score":0.4065999984741211},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11133076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1962065685","https://openalex.org/W1968775993","https://openalex.org/W1979527452","https://openalex.org/W1982439128","https://openalex.org/W1982996921","https://openalex.org/W1984993578","https://openalex.org/W1997162567","https://openalex.org/W2017914730","https://openalex.org/W2018658595","https://openalex.org/W2021211271","https://openalex.org/W2047060659","https://openalex.org/W2053744175","https://openalex.org/W2054604177","https://openalex.org/W2072837011","https://openalex.org/W2080592089","https://openalex.org/W2128120785","https://openalex.org/W2150073849","https://openalex.org/W2511683765","https://openalex.org/W2536535850","https://openalex.org/W2566040696","https://openalex.org/W2605751925","https://openalex.org/W2730499906","https://openalex.org/W2886156724","https://openalex.org/W2895553128","https://openalex.org/W2917720315","https://openalex.org/W2934426651","https://openalex.org/W2950959891","https://openalex.org/W2980229124","https://openalex.org/W3102510044","https://openalex.org/W3117273852","https://openalex.org/W3120481279","https://openalex.org/W3157126516","https://openalex.org/W3181975841","https://openalex.org/W3206857466","https://openalex.org/W4213435190","https://openalex.org/W4221109973","https://openalex.org/W4229618172","https://openalex.org/W4239263365","https://openalex.org/W4249082578","https://openalex.org/W4255138103","https://openalex.org/W4300171661","https://openalex.org/W4312053794","https://openalex.org/W4360831990","https://openalex.org/W4389476360","https://openalex.org/W4392450754","https://openalex.org/W4392910976"],"related_works":[],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"play":[4],"a":[5,38,45,112,155,161],"pivotal":[6],"role":[7],"in":[8,79,158,164],"high-performance":[9],"computing":[10],"by":[11,37],"utilizing":[12],"the":[13,32,61,91,125,173],"massive":[14],"parallelism":[15,27],"of":[16,41,64,94],"concurrent":[17,42],"thread":[18],"execution":[19],"to":[20,101,134,172],"enhance":[21],"processing":[22],"efficiency,":[23],"known":[24],"as":[25],"thread-level":[26],"(TLP).":[28],"However,":[29,54],"effectively":[30],"managing":[31],"significant":[33,46,62],"memory":[34,82,141,150],"access":[35],"generated":[36],"large":[39],"number":[40],"threads":[43],"presents":[44],"challenge,":[47],"affecting":[48],"both":[49,124],"performance":[50,159],"and":[51,127,139,143,160],"energy":[52,165],"consumption.":[53],"previous":[55],"GPU":[56,115],"scheduling":[57,137],"methods":[58],"often":[59],"overlook":[60],"potential":[63,93],"data":[65,86,96,120],"sharing":[66],"among":[67],"non-adjacent":[68,95],"warps":[69],"or":[70],"Cooperative":[71],"Thread":[72],"Arrays":[73],"(CTAs),":[74],"thereby":[75],"limiting":[76],"their":[77],"effectiveness":[78],"reducing":[80],"unnecessary":[81,149],"accesses":[83],"through":[84],"supporting":[85],"sharing.":[87],"Our":[88],"observation":[89],"underscores":[90],"untapped":[92],"sharing,":[97],"motivating":[98],"our":[99],"work":[100],"optimize":[102],"schedules":[103],"more":[104],"effectively.":[105],"In":[106],"this":[107,131],"paper,":[108],"we":[109],"present":[110],"VISTA,":[111],"smart":[113],"locality-aware":[114],"scheduler":[116],"that":[117],"dynamically":[118],"identifies":[119],"locality":[121],"patterns":[122],"at":[123],"CTA":[126],"warp":[128],"levels,":[129],"leveraging":[130],"runtime":[132],"information":[133],"make":[135],"intelligent":[136],"decisions":[138],"improving":[140],"efficiency":[142],"overall":[144],"performance.":[145],"VISTA":[146],"significantly":[147],"reduces":[148],"accesses.":[151],"Simulation":[152],"results":[153],"show":[154],"48.1%":[156],"improvement":[157],"51.8%":[162],"reduction":[163],"consumption":[166],"for":[167],"memory-intensive":[168],"GPGPU":[169],"applications,":[170],"compared":[171],"baseline,":[174],"with":[175],"negligible":[176],"hardware":[177],"overhead.":[178]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}