{"id":"https://openalex.org/W2169049902","doi":"https://doi.org/10.1145/2628071.2628088","title":"Adaptive heterogeneous scheduling for integrated GPUs","display_name":"Adaptive heterogeneous scheduling for integrated GPUs","publication_year":2014,"publication_date":"2014-08-21","ids":{"openalex":"https://openalex.org/W2169049902","doi":"https://doi.org/10.1145/2628071.2628088","mag":"2169049902"},"language":"en","primary_location":{"id":"doi:10.1145/2628071.2628088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628088","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/A5011021816","display_name":"Rashid Kaleem","orcid":null},"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":"Rashid Kaleem","raw_affiliation_strings":["University of Texas, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108643447","display_name":"Rajkishore Barik","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajkishore Barik","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076969648","display_name":"Tatiana Shpeisman","orcid":"https://orcid.org/0000-0002-4225-8734"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tatiana Shpeisman","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111709219","display_name":"Brian T. R. Lewis","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian T. Lewis","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101423312","display_name":"Chunling Hu","orcid":"https://orcid.org/0000-0002-1601-5413"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunling Hu","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013181067","display_name":"Keshav Pingali","orcid":"https://orcid.org/0000-0002-0484-4636"},"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":false,"raw_author_name":"Keshav Pingali","raw_affiliation_strings":["University of Texas, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011021816"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":14.7109,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.99254923,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"162"},"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/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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991000294685364,"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":0.8777425289154053},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6418685913085938},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6317107677459717},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.6097315549850464},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5908610224723816},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5519589185714722},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4206172525882721},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3385903835296631},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24115610122680664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8777425289154053},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6418685913085938},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6317107677459717},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.6097315549850464},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5908610224723816},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5519589185714722},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4206172525882721},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3385903835296631},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24115610122680664},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2628071.2628088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628088","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1460405344","https://openalex.org/W1558412961","https://openalex.org/W1966344015","https://openalex.org/W1970345306","https://openalex.org/W1971081903","https://openalex.org/W1972090741","https://openalex.org/W1982020565","https://openalex.org/W1993338334","https://openalex.org/W2000873501","https://openalex.org/W2008837617","https://openalex.org/W2016352575","https://openalex.org/W2016559894","https://openalex.org/W2020667374","https://openalex.org/W2024122052","https://openalex.org/W2031553682","https://openalex.org/W2033597569","https://openalex.org/W2065392434","https://openalex.org/W2065887019","https://openalex.org/W2068306188","https://openalex.org/W2080592089","https://openalex.org/W2084423328","https://openalex.org/W2091589449","https://openalex.org/W2098903349","https://openalex.org/W2103838950","https://openalex.org/W2115148068","https://openalex.org/W2121893797","https://openalex.org/W2130561688","https://openalex.org/W2132719357","https://openalex.org/W2146757372","https://openalex.org/W2150476673","https://openalex.org/W2167101788","https://openalex.org/W2169875292","https://openalex.org/W2171473263","https://openalex.org/W2561675875","https://openalex.org/W3006997840","https://openalex.org/W4231380462","https://openalex.org/W4232836277","https://openalex.org/W4244327494","https://openalex.org/W4300937065"],"related_works":["https://openalex.org/W2387982802","https://openalex.org/W1896942098","https://openalex.org/W1991061790","https://openalex.org/W2088078730","https://openalex.org/W2400763249","https://openalex.org/W1482063109","https://openalex.org/W2043940072","https://openalex.org/W2249399447","https://openalex.org/W2745443495","https://openalex.org/W2904030423"],"abstract_inverted_index":{"Many":[0],"processors":[1],"today":[2],"integrate":[3],"a":[4,29,42,101],"CPU":[5,37,84,97],"and":[6,21,38,64,85,98,143],"GPU":[7,39,86,99],"on":[8,95,113,139],"the":[9,23,36,77,83,96,114],"same":[10],"die,":[11],"which":[12],"allows":[13],"them":[14],"to":[15,40,74,118],"share":[16],"resources":[17],"like":[18],"physical":[19],"memory":[20],"lowers":[22],"cost":[24],"of":[25,79,137],"CPU-GPU":[26,54],"communication.":[27],"As":[28],"consequence,":[30],"programmers":[31],"can":[32],"effectively":[33],"utilize":[34],"both":[35],"execute":[41],"single":[43],"application.":[44],"This":[45],"paper":[46],"presents":[47],"novel":[48],"adaptive":[49],"scheduling":[50,61,68,160],"techniques":[51],"for":[52],"integrated":[53],"processors.":[55],"We":[56],"present":[57],"two":[58],"online":[59,72],"profiling-based":[60],"algorithms:":[62],"na\u00efve":[63],"asymmetric.":[65],"Our":[66],"asymmetric":[67],"algorithm":[69,161],"uses":[70],"low-overhead":[71],"profiling":[73,94],"automatically":[75],"partition":[76],"work":[78,138],"data-parallel":[80],"kernels":[81,146],"between":[82],"without":[87],"input":[88],"from":[89],"application":[90,119],"developers.":[91],"It":[92,116],"does":[93,162],"in":[100],"way":[102],"that":[103,109],"it":[104],"doesn't":[105],"penalize":[106],"GPU-centric":[107],"workloads":[108],"run":[110],"significantly":[111],"faster":[112],"GPU.":[115],"adapts":[117],"characteristics":[120],"by":[121],"addressing:":[122],"1)":[123],"load":[124],"imbalance":[125],"via":[126],"irregularity":[127],"caused":[128],"by,":[129],"e.g.,":[130],"data-dependent":[131],"control":[132],"flow,":[133],"2)":[134],"different":[135,148],"amounts":[136],"each":[140],"kernel":[141],"call,":[142],"3)":[144],"multiple":[145],"with":[147],"characteristics.":[149],"Unlike":[150],"many":[151],"existing":[152],"approaches":[153],"primarily":[154],"targeting":[155],"NVIDIA":[156],"discrete":[157],"GPUs,":[158],"our":[159],"not":[163],"require":[164],"offline":[165],"processing.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":12}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}