{"id":"https://openalex.org/W2622662087","doi":"https://doi.org/10.1145/3075564.3075567","title":"Work Stealing in a Shared Virtual-Memory Heterogeneous Environment","display_name":"Work Stealing in a Shared Virtual-Memory Heterogeneous Environment","publication_year":2017,"publication_date":"2017-05-15","ids":{"openalex":"https://openalex.org/W2622662087","doi":"https://doi.org/10.1145/3075564.3075567","mag":"2622662087"},"language":"en","primary_location":{"id":"doi:10.1145/3075564.3075567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3075564.3075567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Computing Frontiers Conference","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/A5018356320","display_name":"Shuai Che","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Shuai Che","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003216606","display_name":"Marc S. Orr","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marc Orr","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089479282","display_name":"Jonathan Gallmeier","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jonathan Gallmeier","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018356320"],"corresponding_institution_ids":["https://openalex.org/I1311921367"],"apc_list":null,"apc_paid":null,"fwci":1.9345,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89241826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"164","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8931609988212585},{"id":"https://openalex.org/keywords/betweenness-centrality","display_name":"Betweenness centrality","score":0.7965878248214722},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6109334230422974},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5969499945640564},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5834986567497253},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.5018272399902344},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.48871397972106934},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.47811856865882874},{"id":"https://openalex.org/keywords/virtual-machine","display_name":"Virtual machine","score":0.4516432285308838},{"id":"https://openalex.org/keywords/centrality","display_name":"Centrality","score":0.2980256676673889},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26034408807754517},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20460033416748047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8931609988212585},{"id":"https://openalex.org/C117045392","wikidata":"https://www.wikidata.org/wiki/Q4899215","display_name":"Betweenness centrality","level":3,"score":0.7965878248214722},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6109334230422974},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5969499945640564},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5834986567497253},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.5018272399902344},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.48871397972106934},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.47811856865882874},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.4516432285308838},{"id":"https://openalex.org/C53811970","wikidata":"https://www.wikidata.org/wiki/Q5062194","display_name":"Centrality","level":2,"score":0.2980256676673889},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26034408807754517},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20460033416748047},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3075564.3075567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3075564.3075567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Computing Frontiers Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W780656674","https://openalex.org/W1460405344","https://openalex.org/W1987396134","https://openalex.org/W1993239831","https://openalex.org/W1998460673","https://openalex.org/W2014724071","https://openalex.org/W2016559894","https://openalex.org/W2016706026","https://openalex.org/W2035080386","https://openalex.org/W2041470524","https://openalex.org/W2092703362","https://openalex.org/W2104861744","https://openalex.org/W2107251158","https://openalex.org/W2109639089","https://openalex.org/W2121893797","https://openalex.org/W2150476673","https://openalex.org/W2171707538","https://openalex.org/W2416330002","https://openalex.org/W2417359092","https://openalex.org/W2502480331","https://openalex.org/W2913844511","https://openalex.org/W2951135776","https://openalex.org/W3020940081","https://openalex.org/W6724916451"],"related_works":["https://openalex.org/W1516497519","https://openalex.org/W2356738361","https://openalex.org/W2012724202","https://openalex.org/W3006871705","https://openalex.org/W4205555748","https://openalex.org/W2166456073","https://openalex.org/W2886295835","https://openalex.org/W2118175818","https://openalex.org/W3144459458","https://openalex.org/W2339099243"],"abstract_inverted_index":{"This":[0],"paper":[1],"uses":[2],"betweenness":[3,141],"centrality":[4,20,142],"as":[5],"a":[6,15,92],"case":[7],"study":[8],"to":[9,37,46,75,87,153,172],"research":[10],"efficient":[11],"work":[12,44,102,145,165],"stealing":[13,45,103,146,166],"in":[14,25,91,95],"heterogeneous":[16,133],"system":[17,134],"environment.":[18],"Betweenness":[19],"is":[21,33],"an":[22,34,148],"important":[23,179],"algorithm":[24],"graph":[26,162],"processing.":[27],"It":[28],"presents":[29],"multiple-level":[30],"parallelism":[31],"and":[32,55,59,105,122,184],"interesting":[35],"problem":[36],"exploit":[38],"various":[39],"optimizations.":[40],"We":[41,128],"investigate":[42],"queue-based":[43],"distribute":[47],"its":[48],"tasks":[49],"across":[50,56],"GPU":[51],"compute":[52],"units":[53],"(CUs)":[54],"the":[57,60,77,101,106],"CPU":[58],"GPU,":[61],"which":[62],"has":[63],"not":[64],"been":[65],"done":[66],"by":[67],"prior":[68],"work.":[69],"In":[70],"particular,":[71],"we":[72,110,177],"demonstrate":[73],"how":[74],"leverage":[76],"new":[78,112],"platform-atomic":[79],"operations":[80,117],"on":[81],"AMD":[82],"Accelerated":[83],"Processing":[84],"Units":[85],"(APUs)":[86],"operate":[88],"cross-device":[89],"queues":[90],"lock-free":[93],"manner":[94],"shared":[96],"virtual":[97],"memory.":[98],"To":[99],"make":[100],"runtime":[104],"application":[107],"more":[108],"efficient,":[109],"apply":[111],"architectural":[113],"features,":[114],"including":[115],"atomic":[116],"with":[118,143],"different":[119,125],"memory":[120],"scopes":[121],"or-derings":[123],"for":[124,160,182],"synchronization":[126],"scenarios.":[127],"implement":[129],"our":[130],"solution":[131,167],"using":[132],"architecture":[135],"(HSA).":[136],"Our":[137,164],"results":[138],"show":[139],"that":[140],"CPU-GPU":[144],"achieves":[147],"average":[149],"of":[150],"15%":[151],"(up":[152],"30%)":[154],"performance":[155],"improvement":[156],"over":[157],"GPU-only":[158],"execution":[159],"diverse":[161],"inputs.":[163],"can":[168],"be":[169],"applied":[170],"widely":[171],"other":[173],"applications":[174],"too.":[175],"Finally,":[176],"analyze":[178],"parameters":[180],"critical":[181],"queuing":[183],"stealing.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
