{"id":"https://openalex.org/W2995857810","doi":"https://doi.org/10.1147/jrd.2019.2960245","title":"Hybrid CPU/GPU tasks optimized for concurrency in OpenMP","display_name":"Hybrid CPU/GPU tasks optimized for concurrency in OpenMP","publication_year":2019,"publication_date":"2019-12-17","ids":{"openalex":"https://openalex.org/W2995857810","doi":"https://doi.org/10.1147/jrd.2019.2960245","mag":"2995857810"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2019.2960245","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2019.2960245","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","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/A5068763494","display_name":"Alexandre E. Eichenberger","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"A. E. Eichenberger","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028956723","display_name":"Gheorghe-Teodor Bercea","orcid":"https://orcid.org/0000-0003-4331-4360"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G.-T. Bercea","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018762393","display_name":"Alexey Bataev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Bataev","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003878251","display_name":"Lea T. Grinberg","orcid":"https://orcid.org/0000-0002-6809-0618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L. Grinberg","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041893114","display_name":"John K. P. O'Brien","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. K. O'Brien","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068763494"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52582833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"64","issue":"3/4","first_page":"13:1","last_page":"13:14"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994000196456909,"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":0.9990000128746033,"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":0.9042739868164062},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7380276918411255},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6286240816116333},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5143864750862122},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.46252521872520447},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.46050187945365906},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43162888288497925},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4169906973838806},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3645612597465515},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.19605466723442078},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1602928340435028},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08806419372558594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9042739868164062},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7380276918411255},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6286240816116333},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5143864750862122},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.46252521872520447},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.46050187945365906},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43162888288497925},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4169906973838806},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3645612597465515},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.19605466723442078},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1602928340435028},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08806419372558594},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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":1,"locations":[{"id":"doi:10.1147/jrd.2019.2960245","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2019.2960245","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3608418543","display_name":null,"funder_award_id":"B604142","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W47306539","https://openalex.org/W1531079003","https://openalex.org/W2014071176","https://openalex.org/W2019028742","https://openalex.org/W2051377984","https://openalex.org/W2072725684","https://openalex.org/W2098147619","https://openalex.org/W2121893797","https://openalex.org/W2142677441","https://openalex.org/W2985428643","https://openalex.org/W4242979982","https://openalex.org/W4294549613"],"related_works":["https://openalex.org/W207411050","https://openalex.org/W2974157558","https://openalex.org/W2950520577","https://openalex.org/W1501159154","https://openalex.org/W4387237598","https://openalex.org/W74409296","https://openalex.org/W2003935582","https://openalex.org/W2567390125","https://openalex.org/W4405088460","https://openalex.org/W1554644772"],"abstract_inverted_index":{"Sierra":[0],"and":[1,16,43,59,90,154,180],"Summit":[2],"supercomputers":[3],"exhibit":[4],"a":[5,101,117],"significant":[6],"amount":[7],"of":[8,52,65,82,104,171,185],"intranode":[9,69],"parallelism":[10,29,53,70],"between":[11,194],"the":[12,63,72,80,97,131,151,159,169,198],"host":[13,160],"POWER9":[14],"CPUs":[15],"their":[17,91],"attached":[18],"GPU":[19,44,137,148,181,187,195,201],"devices.":[20],"In":[21],"this":[22,50,67],"article,":[23],"we":[24],"show":[25],"that":[26,120,128],"exploiting":[27,49,66],"device-level":[28],"is":[30,57],"key":[31,165],"to":[32,85,107,136,147,158,167,197,203],"achieving":[33],"high":[34],"performance":[35],"by":[36,175],"reducing":[37],"overheads":[38],"typically":[39],"associated":[40,92],"with":[41],"CPU":[42,98,113,161],"task":[45,88,125],"execution.":[46],"Moreover,":[47],"manually":[48],"type":[51],"in":[54],"large-scale":[55],"applications":[56],"nontrivial":[58],"error-prone.":[60],"We":[61,115,163,189],"hide":[62],"complexity":[64],"hybrid":[68],"using":[71],"OpenMP":[73,83],"programming":[74],"model":[75],"abstraction.":[76],"The":[77],"implementation":[78],"leverages":[79],"semantics":[81],"tasks":[84,95,196],"express":[86],"asynchronous":[87,186,200],"computations":[89,182],"dependences.":[93],"Launching":[94],"on":[96,130],"threads":[99],"requires":[100],"careful":[102],"design":[103],"work-stealing":[105],"algorithms":[106],"provide":[108],"efficient":[109],"load":[110],"balancing":[111],"among":[112],"threads.":[114],"propose":[116],"novel":[118],"algorithm":[119],"removes":[121],"locks":[122],"from":[123],"all":[124],"queueing":[126],"operations":[127],"are":[129],"critical":[132],"path.":[133],"Tasks":[134],"assigned":[135],"devices":[138],"require":[139],"additional":[140,173],"steps":[141,174],"such":[142],"as":[143],"copying":[144,155],"input":[145],"data":[146,156,178],"devices,":[149],"launching":[150],"computation":[152],"kernels,":[153],"back":[157],"memory.":[162],"perform":[164],"optimizations":[166],"reduce":[168],"cost":[170],"these":[172],"tightly":[176],"integrating":[177],"transfers":[179],"into":[183],"streams":[184,202],"operations.":[188],"further":[190,204],"map":[191],"high-level":[192],"dependences":[193],"same":[199],"avoid":[205],"unnecessary":[206],"synchronization.":[207],"Results":[208],"validate":[209],"our":[210],"approach.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}