{"id":"https://openalex.org/W2065383439","doi":"https://doi.org/10.1109/ipdpsw.2013.256","title":"Synchronization and Ordering Semantics in Hybrid MPI+GPU Programming","display_name":"Synchronization and Ordering Semantics in Hybrid MPI+GPU Programming","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2065383439","doi":"https://doi.org/10.1109/ipdpsw.2013.256","mag":"2065383439"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2013.256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2013.256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","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/A5091417392","display_name":"Ashwin M. Aji","orcid":"https://orcid.org/0000-0002-5467-8357"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ashwin M. Aji","raw_affiliation_strings":["Dept. of Computer Science, Virginia Tech","Virginia Tech, Blacksburg, United States"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Virginia Tech","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Tech, Blacksburg, United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050531633","display_name":"Pavan Balaji","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavan Balaji","raw_affiliation_strings":["Argonne National Laboratory, Lemont, United States"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, United States","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078425310","display_name":"James Dinan","orcid":"https://orcid.org/0000-0002-4840-7737"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Dinan","raw_affiliation_strings":["Math. and Comp. Sci. Div., Argonne National Lab","Argonne National Laboratory, Lemont, United States"],"affiliations":[{"raw_affiliation_string":"Math. and Comp. Sci. Div., Argonne National Lab","institution_ids":[]},{"raw_affiliation_string":"Argonne National Laboratory, Lemont, United States","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu-chun Feng","raw_affiliation_strings":["Math. and Comp. Sci. Div., Argonne National Lab","Virginia Tech, Blacksburg, United States"],"affiliations":[{"raw_affiliation_string":"Math. and Comp. Sci. Div., Argonne National Lab","institution_ids":[]},{"raw_affiliation_string":"Virginia Tech, Blacksburg, United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014920685","display_name":"Rajeev Thakur","orcid":"https://orcid.org/0000-0002-5532-3048"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajeev Thakur","raw_affiliation_strings":["Math. and Comp. Sci. Div., Argonne National Lab","Argonne National Laboratory, Lemont, United States"],"affiliations":[{"raw_affiliation_string":"Math. and Comp. Sci. Div., Argonne National Lab","institution_ids":[]},{"raw_affiliation_string":"Argonne National Laboratory, Lemont, United States","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091417392"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.6343,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70691586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1020","last_page":"1029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9965999722480774,"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":0.9046578407287598},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6311372518539429},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5878261923789978},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.5831196308135986},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5556744933128357},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5139260292053223},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5115362405776978},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38949912786483765},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2757229804992676},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13704964518547058},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.09448355436325073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9046578407287598},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6311372518539429},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5878261923789978},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.5831196308135986},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5556744933128357},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5139260292053223},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5115362405776978},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38949912786483765},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2757229804992676},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13704964518547058},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.09448355436325073},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ipdpsw.2013.256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2013.256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.833","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mcs.anl.gov/~thakur/papers/mpiacc-ordering.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.8093","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.8093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://synergy.cs.vt.edu/pubs/papers/aji-ashes13-mpiacc-ordering.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1965378199","https://openalex.org/W2012173227","https://openalex.org/W2040561634","https://openalex.org/W2056687467","https://openalex.org/W2070940137","https://openalex.org/W2116508956","https://openalex.org/W2129003192","https://openalex.org/W2150639558","https://openalex.org/W2162142618","https://openalex.org/W2165949232","https://openalex.org/W2167173222","https://openalex.org/W2168363974","https://openalex.org/W2399715892","https://openalex.org/W2476176513","https://openalex.org/W3141032579"],"related_works":["https://openalex.org/W4385894176","https://openalex.org/W2347371119","https://openalex.org/W2612768808","https://openalex.org/W3131402800","https://openalex.org/W2388965158","https://openalex.org/W2366201982","https://openalex.org/W2808480228","https://openalex.org/W2593071546","https://openalex.org/W2805641962","https://openalex.org/W1571189856"],"abstract_inverted_index":{"Despite":[0],"the":[1,24,31,63,103,119],"vast":[2],"interest":[3],"in":[4,59],"accelerator-based":[5],"systems,":[6],"programming":[7],"large":[8],"multinode":[9],"GPUs":[10],"is":[11,106],"still":[12],"a":[13],"complex":[14],"task,":[15],"particularly":[16],"with":[17,111],"respect":[18],"to":[19,35,62,71],"optimal":[20],"data":[21,48,113],"movement":[22,49],"across":[23,30],"host-GPU":[25],"PCIe":[26],"connection":[27],"and":[28,66,83,98,100,130],"then":[29],"network.":[32],"In":[33,88],"order":[34],"address":[36],"such":[37],"issues,":[38],"GPU-integrated":[39,56],"MPI":[40,52,85,129],"solutions":[41],"have":[42],"been":[43],"developed":[44],"that":[45,102],"integrate":[46],"GPU":[47,131],"into":[50],"existing":[51],"implementations.":[53],"Currently":[54],"available":[55],"frameworks":[57],"differ":[58],"aspects":[60],"related":[61],"buffer":[64],"synchronization":[65],"ordering":[67,116],"semantics":[68],"they":[69],"provide":[70],"users.":[72],"The":[73],"noteworthy":[74],"models":[75],"are":[76,133],"(1)":[77],"unified":[78],"virtual":[79],"addressing":[80],"(UVA)-based":[81],"approach":[82],"(2)":[84],"attributes-based":[86,120],"approach.":[87],"this":[89],"paper,":[90],"we":[91],"compare":[92],"these":[93],"approaches,":[94],"for":[95,108],"both":[96],"programmability":[97],"performance,":[99],"demonstrate":[101],"UVA-based":[104],"design":[105,121],"useful":[107],"isolated":[109],"communication":[110],"no":[112],"dependencies":[114],"or":[115],"requirements,":[117],"while":[118],"might":[122],"be":[123],"more":[124],"appropriate":[125],"when":[126],"multiple":[127],"interdependent":[128],"operations":[132],"interleaved.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"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"}