{"id":"https://openalex.org/W3133730715","doi":"https://doi.org/10.1145/3453953.3453972","title":"Demystifying the Placement Policies of the NVIDIA GPU Thread Block Scheduler for Concurrent Kernels","display_name":"Demystifying the Placement Policies of the NVIDIA GPU Thread Block Scheduler for Concurrent Kernels","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3133730715","doi":"https://doi.org/10.1145/3453953.3453972","mag":"3133730715"},"language":"en","primary_location":{"id":"doi:10.1145/3453953.3453972","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453953.3453972","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","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/A5012915347","display_name":"Guin Gilman","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guin Gilman","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041264523","display_name":"Samuel S. Ogden","orcid":"https://orcid.org/0000-0003-2851-4129"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel S. Ogden","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051346938","display_name":"Tian Guo","orcid":"https://orcid.org/0000-0003-0060-2266"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Guo","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076667950","display_name":"Robert J. Walls","orcid":"https://orcid.org/0000-0002-1338-6403"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert J. Walls","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":3.7772,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.93448645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"48","issue":"3","first_page":"81","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9984999895095825,"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":0.86588454246521},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7595711350440979},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7458073496818542},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5768169164657593},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.5223892331123352},{"id":"https://openalex.org/keywords/computer-multitasking","display_name":"Computer multitasking","score":0.4137926697731018},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.40084946155548096},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12323242425918579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86588454246521},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7595711350440979},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7458073496818542},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5768169164657593},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.5223892331123352},{"id":"https://openalex.org/C154556556","wikidata":"https://www.wikidata.org/wiki/Q192969","display_name":"Computer multitasking","level":2,"score":0.4137926697731018},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.40084946155548096},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12323242425918579},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3453953.3453972","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453953.3453972","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1994001225","https://openalex.org/W2030675942","https://openalex.org/W2080592089","https://openalex.org/W2097643185","https://openalex.org/W2098274770","https://openalex.org/W2125551452","https://openalex.org/W2150851481","https://openalex.org/W2409247164","https://openalex.org/W2510980549","https://openalex.org/W2764065518","https://openalex.org/W2766210752","https://openalex.org/W2786171709","https://openalex.org/W2796649226","https://openalex.org/W2906773779","https://openalex.org/W2920798074","https://openalex.org/W2952562115","https://openalex.org/W4233727362","https://openalex.org/W4243035950","https://openalex.org/W4289083201"],"related_works":["https://openalex.org/W2044703812","https://openalex.org/W2024449400","https://openalex.org/W2015730180","https://openalex.org/W2093823425","https://openalex.org/W1976357998","https://openalex.org/W1997832768","https://openalex.org/W2037029453","https://openalex.org/W2023832055","https://openalex.org/W2082485924","https://openalex.org/W2037535956"],"abstract_inverted_index":{"In":[0,19],"this":[1,60],"work,":[2],"we":[3,40],"empirically":[4],"derive":[5],"the":[6,26,44,47,52,105,113],"scheduler's":[7],"behavior":[8],"under":[9],"concurrent":[10],"workloads":[11],"for":[12,72,89,103],"NVIDIA's":[13],"Pascal,":[14],"Volta,":[15],"and":[16,67,110],"Turing":[17],"microarchitectures.":[18],"contrast":[20],"to":[21,32,36,65],"past":[22],"studies":[23],"that":[24,43,97],"suggest":[25],"scheduler":[27,45],"uses":[28],"a":[29,74,83],"round-robin":[30],"policy":[31,62],"assign":[33],"thread":[34,78],"blocks":[35],"streaming":[37],"multiprocessors":[38],"(SMs),":[39],"instead":[41],"find":[42],"chooses":[46],"next":[48],"SM":[49],"based":[50],"on":[51],"SM's":[53],"local":[54],"resource":[55],"availability.":[56],"We":[57,95],"show":[58],"how":[59],"scheduling":[61,117],"can":[63],"lead":[64],"significant,":[66],"seemingly":[68],"counter-intuitive,":[69],"performance":[70],"degradation;":[71],"example,":[73],"decrease":[75],"of":[76,107,115],"one":[77,90],"per":[79],"block":[80],"resulted":[81],"in":[82,86,92,112],"3.58X":[84],"increase":[85],"execution":[87],"time":[88],"kernel":[91],"our":[93,98],"experiments.":[94],"hope":[96],"work":[99],"will":[100],"be":[101],"useful":[102],"improving":[104],"accuracy":[106],"GPU":[108],"simulators":[109],"aid":[111],"development":[114],"novel":[116],"algorithms.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
