{"id":"https://openalex.org/W2018767489","doi":"https://doi.org/10.1145/2628071.2628117","title":"Preemptive thread block scheduling with online structural runtime prediction for concurrent GPGPU kernels","display_name":"Preemptive thread block scheduling with online structural runtime prediction for concurrent GPGPU kernels","publication_year":2014,"publication_date":"2014-08-21","ids":{"openalex":"https://openalex.org/W2018767489","doi":"https://doi.org/10.1145/2628071.2628117","mag":"2018767489"},"language":"en","primary_location":{"id":"doi:10.1145/2628071.2628117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","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/A5006053754","display_name":"Sreepathi Pai","orcid":"https://orcid.org/0000-0002-3691-7238"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sreepathi Pai","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA","The University of Texas At Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas At Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113510967","display_name":"R. Govindarajan","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R. Govindarajan","raw_affiliation_strings":["Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027487670","display_name":"Matthew J. Thazhuthaveetil","orcid":"https://orcid.org/0009-0007-1550-8121"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Matthew J. Thazhuthaveetil","raw_affiliation_strings":["Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006053754"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.8903,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.85244225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"483","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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":0.8845646381378174},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7105796337127686},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.701330304145813},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.53645920753479},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.47883060574531555},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.438781201839447},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.4195803701877594},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3620187044143677},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.34167540073394775},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3292704224586487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8845646381378174},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7105796337127686},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.701330304145813},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.53645920753479},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.47883060574531555},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.438781201839447},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.4195803701877594},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3620187044143677},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.34167540073394775},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3292704224586487},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2628071.2628117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.9662","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.9662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://drona.csa.iisc.ernet.in/~mjt/papers/pact2014.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.748.6570","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.748.6570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1406.6037.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2018767489"],"related_works":["https://openalex.org/W2505380084","https://openalex.org/W2086739451","https://openalex.org/W3183233360","https://openalex.org/W2033778626","https://openalex.org/W2073137634","https://openalex.org/W2026780467","https://openalex.org/W641925902","https://openalex.org/W2082509836","https://openalex.org/W2149904643","https://openalex.org/W2102668194"],"abstract_inverted_index":{"Recent":[0],"NVIDIA":[1],"Graphics":[2],"Processing":[3],"Units":[4],"(GPUs)":[5],"can":[6,86,128,156],"execute":[7],"multiple":[8],"kernels":[9,251],"concurrently.":[10],"On":[11],"these":[12],"GPUs,":[13],"the":[14,21,34,58,84,123,134,158,164,190,294],"thread":[15,26,137,170,176],"block":[16,177],"scheduler":[17,178],"(TBS)":[18],"currently":[19],"uses":[20,185],"FIFO":[22,35,297],"policy":[23,36,65,196,224],"to":[24,39,218,252,268,278],"schedule":[25],"blocks":[27],"of":[28,45,57,72,74,83,116,125,166,248,273,281,293],"concurrent":[29,182,226],"kernels.":[30],"We":[31,139,188],"show":[32,78,121],"that":[33,79,122,154,179],"leaves":[37],"performance":[38,46,51],"chance,":[40],"resulting":[41],"in":[42],"significant":[43],"loss":[44],"and":[47,52,93,152,184,197,210,233,263,298],"fairness.":[48,254],"To":[49,237],"improve":[50,238],"fairness,":[53,239],"we":[54,77,104,120,173,240],"propose":[55,105,242],"use":[56],"preemptive":[59],"Shortest":[60,191,282],"Remaining":[61,192],"Time":[62,193],"First":[63,194,284],"(SRTF)":[64,195],"instead.":[66],"Although":[67],"SRTF":[68,205,228,274],"requires":[69],"an":[70,81,141,286],"estimate":[71,82,157],"runtime":[73,85,124,160],"GPU":[75,99,117],"kernels,":[76,227],"such":[80],"be":[87,129],"easily":[88],"obtained":[89],"using":[90],"online":[91,142],"profiling":[92,132],"exploiting":[94],"a":[95,106,112,126,168,175,220],"simple":[96,113],"observation":[97],"on":[98,145,148,200],"kernels'":[100],"grid":[101],"structure.":[102],"Specifically,":[103],"novel":[107],"Structural":[108],"Runtime":[109],"Predictor.":[110],"Using":[111],"Staircase":[114],"model":[115,147],"kernel":[118,127],"execution,":[119],"predicted":[130],"by":[131,208,212,231,235,258,261,265],"only":[133,167],"first":[135],"few":[136],"blocks.":[138],"evaluate":[140,198],"predictor":[143],"based":[144],"this":[146,186],"benchmarks":[149],"from":[150,203],"ERCBench,":[151],"find":[153],"it":[155,199],"actual":[159],"reasonably":[161],"well":[162],"after":[163],"execution":[165],"single":[169],"block.":[171],"Next,":[172],"design":[174],"is":[180],"both":[181],"kernel-aware":[183],"predictor.":[187],"implement":[189],"two-program":[201],"workloads":[202],"ER-CBench.":[204],"improves":[206,229,256],"STP":[207,230,257],"1.18x":[209],"ANTT":[211,234,260],"2.25x":[213],"over":[214],"FIFO.":[215,269],"When":[216],"compared":[217,267],"MPMax,":[219],"state-of-the-art":[221],"resource":[222,246],"allocation":[223],"for":[225],"1.16x":[232],"1.3x.":[236],"also":[241],"SRTF/Adaptive":[243,255],"which":[244],"controls":[245],"usage":[247],"concurrently":[249],"executing":[250],"maximize":[253],"1.12x,":[259],"2.23x":[262],"Fairness":[264],"2.95x":[266],"Overall,":[270],"our":[271],"implementation":[272],"achieves":[275],"system":[276],"throughput":[277],"within":[279],"12.64%":[280],"Job":[283],"(SJF,":[285],"oracle":[287],"optimal":[288],"scheduling":[289],"policy),":[290],"bridging":[291],"49%":[292],"gap":[295],"between":[296],"SJF.":[299]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}