{"id":"https://openalex.org/W2767144262","doi":"https://doi.org/10.1145/3148173.3148189","title":"Implementing implicit OpenMP data sharing on GPUs","display_name":"Implementing implicit OpenMP data sharing on GPUs","publication_year":2017,"publication_date":"2017-10-31","ids":{"openalex":"https://openalex.org/W2767144262","doi":"https://doi.org/10.1145/3148173.3148189","mag":"2767144262"},"language":"en","primary_location":{"id":"doi:10.1145/3148173.3148189","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148173.3148189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Workshop on the LLVM Compiler Infrastructure in HPC","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.10413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gheorghe-Teodor Bercea","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gheorghe-Teodor Bercea","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Carlo Bertolli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlo Bertolli","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arpith C. Jacob","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arpith C. Jacob","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alexandre Eichenberger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandre Eichenberger","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alexey Bataev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexey Bataev","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Georgios Rokos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgios Rokos","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyojin Sung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyojin Sung","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Chen","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Kevin O'Brien","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin O'Brien","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1181,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79778527,"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":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/toolchain","display_name":"Toolchain","score":0.8399999737739563},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8319000005722046},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5928999781608582},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5845999717712402},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48570001125335693},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.4083000123500824},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.375},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3361999988555908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507999777793884},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.8399999737739563},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8319000005722046},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7311999797821045},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5928999781608582},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4828999936580658},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.4083000123500824},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.375},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C2776937656","wikidata":"https://www.wikidata.org/wiki/Q2229669","display_name":"Nesting (process)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.26579999923706055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3148173.3148189","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148173.3148189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Workshop on the LLVM Compiler Infrastructure in HPC","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1711.10413","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.10413","pdf_url":"https://arxiv.org/pdf/1711.10413","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1711.10413","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.10413","pdf_url":"https://arxiv.org/pdf/1711.10413","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W35325240","https://openalex.org/W2019143817","https://openalex.org/W2180288011","https://openalex.org/W2294178969","https://openalex.org/W2786644468","https://openalex.org/W4234180294","https://openalex.org/W4236883517"],"related_works":[],"abstract_inverted_index":{"OpenMP":[0,41,52],"is":[1,61],"a":[2,27,85,115],"shared":[3,110],"memory":[4,79],"programming":[5],"model":[6],"which":[7],"supports":[8,33],"the":[9,35,40,49,62,95,112],"offloading":[10,43],"of":[11,51,55,97,103,114],"target":[12],"regions":[13,98],"to":[14,25,76,84,91,107],"accelerators":[15],"such":[16,59],"as":[17],"NVIDIA":[18],"GPUs.":[19],"The":[20],"implementation":[21],"in":[22],"Clang/LLVM":[23],"aims":[24],"deliver":[26],"generic":[28],"GPU":[29],"compilation":[30],"toolchain":[31],"that":[32,93],"both":[34],"native":[36],"CUDA":[37,56,86],"C/C++":[38],"and":[39,53,80],"device":[42],"models.":[44],"There":[45],"are":[46,73],"situations":[47],"where":[48],"semantics":[50,92],"those":[54],"diverge.":[57],"One":[58],"example":[60],"policy":[63],"for":[64],"implicitly":[65,74,109],"handling":[66],"local":[67,71,78],"variables.":[68],"In":[69,88],"CUDA,":[70],"variables":[72,105],"mapped":[75],"thread":[77],"thus":[81],"become":[82],"private":[83],"thread.":[87],"OpenMP,":[89],"due":[90],"allow":[94],"nesting":[96],"executed":[99],"by":[100],"different":[101],"numbers":[102],"threads,":[104],"need":[106],"be":[108],"among":[111],"threads":[113],"contention":[116],"group.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2017-11-10T00:00:00"}
