{"id":"https://openalex.org/W2051507892","doi":"https://doi.org/10.1145/2807591.2807602","title":"Improving concurrency and asynchrony in multithreaded MPI applications using software offloading","display_name":"Improving concurrency and asynchrony in multithreaded MPI applications using software offloading","publication_year":2015,"publication_date":"2015-10-27","ids":{"openalex":"https://openalex.org/W2051507892","doi":"https://doi.org/10.1145/2807591.2807602","mag":"2051507892"},"language":"en","primary_location":{"id":"doi:10.1145/2807591.2807602","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2807591.2807602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1970188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110182945","display_name":"Karthikeyan Vaidyanathan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Karthikeyan Vaidyanathan","raw_affiliation_strings":["Parallel Computing Lab, Intel"],"affiliations":[{"raw_affiliation_string":"Parallel Computing Lab, Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018944355","display_name":"Dhiraj Kalamkar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dhiraj D. Kalamkar","raw_affiliation_strings":["Parallel Computing Lab, Intel"],"affiliations":[{"raw_affiliation_string":"Parallel Computing Lab, Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009048048","display_name":"Kiran Pamnany","orcid":"https://orcid.org/0009-0009-2340-3658"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kiran Pamnany","raw_affiliation_strings":["Parallel Computing Lab, Intel"],"affiliations":[{"raw_affiliation_string":"Parallel Computing Lab, Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081388506","display_name":"Jeff R. Hammond","orcid":"https://orcid.org/0000-0003-3181-8190"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jeff R. Hammond","raw_affiliation_strings":["Parallel Computing Lab, Intel"],"affiliations":[{"raw_affiliation_string":"Parallel Computing Lab, Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"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","argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103810955","display_name":"Dipankar Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dipankar Das","raw_affiliation_strings":["Parallel Computing Lab, Intel"],"affiliations":[{"raw_affiliation_string":"Parallel Computing Lab, Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101876582","display_name":"Jongsoo Park","orcid":"https://orcid.org/0000-0002-4750-9440"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jongsoo Park","raw_affiliation_strings":["Parallel Computing Lab, Intel"],"affiliations":[{"raw_affiliation_string":"Parallel Computing Lab, Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038029051","display_name":"B\u00e1lint Jo\u00f3","orcid":"https://orcid.org/0000-0002-4229-7960"},"institutions":[{"id":"https://openalex.org/I29801172","display_name":"Thomas Jefferson National Accelerator Facility","ror":"https://ror.org/02vwzrd76","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I29801172","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"B\u00e1lint Jo\u00f3","raw_affiliation_strings":["Thomas Jefferson National Accelerator Facility"],"affiliations":[{"raw_affiliation_string":"Thomas Jefferson National Accelerator Facility","institution_ids":["https://openalex.org/I29801172"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5110182945"],"corresponding_institution_ids":["https://openalex.org/I4210158342"],"apc_list":null,"apc_paid":null,"fwci":4.6457,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94928864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"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":0.9995999932289124,"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":0.9977999925613403,"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":0.8865113258361816},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.832319974899292},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7629422545433044},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6028413772583008},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.5844631791114807},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.5398184061050415},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.539067804813385},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5265898108482361},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5099681615829468},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.49969911575317383},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47289907932281494},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46122580766677856},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.45619162917137146},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.44098711013793945},{"id":"https://openalex.org/keywords/asynchrony","display_name":"Asynchrony (computer programming)","score":0.41261613368988037},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3232797384262085},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19407901167869568},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15962481498718262},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09518939256668091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8865113258361816},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.832319974899292},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7629422545433044},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6028413772583008},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.5844631791114807},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.5398184061050415},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.539067804813385},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5265898108482361},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5099681615829468},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.49969911575317383},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47289907932281494},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46122580766677856},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45619162917137146},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.44098711013793945},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.41261613368988037},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3232797384262085},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19407901167869568},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15962481498718262},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09518939256668091}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2807591.2807602","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2807591.2807602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1970188","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1970188","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1970188","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1970188","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.8100000023841858,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1521427322","https://openalex.org/W1563686443","https://openalex.org/W1579891937","https://openalex.org/W1598866093","https://openalex.org/W1897240848","https://openalex.org/W1973698443","https://openalex.org/W1980670496","https://openalex.org/W1990294766","https://openalex.org/W2032654702","https://openalex.org/W2050120016","https://openalex.org/W2061171222","https://openalex.org/W2072897844","https://openalex.org/W2096263410","https://openalex.org/W2102182691","https://openalex.org/W2104994660","https://openalex.org/W2117539524","https://openalex.org/W2119372979","https://openalex.org/W2123859357","https://openalex.org/W2126688073","https://openalex.org/W2130861794","https://openalex.org/W2134557905","https://openalex.org/W2136171935","https://openalex.org/W2155216327","https://openalex.org/W2159826908","https://openalex.org/W2263589951","https://openalex.org/W2295191825","https://openalex.org/W2316564661","https://openalex.org/W2611016860","https://openalex.org/W3101208208","https://openalex.org/W6633628269","https://openalex.org/W6675507917","https://openalex.org/W6693309132","https://openalex.org/W6737062067"],"related_works":["https://openalex.org/W2534656837","https://openalex.org/W2374603670","https://openalex.org/W2061653780","https://openalex.org/W4300245965","https://openalex.org/W2414929729","https://openalex.org/W2963792515","https://openalex.org/W2148036958","https://openalex.org/W2103261828","https://openalex.org/W2133675875","https://openalex.org/W4320502881"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,20,45,88],"new":[3],"approach":[4,70],"for":[5,56,97,120,141],"multithreaded":[6],"communication":[7,17,49,63,82,90,99],"and":[8,64,132,145],"asynchronous":[9],"progress":[10,96],"in":[11,39,117],"MPI":[12,40,76],"applications,":[13],"wherein":[14],"we":[15,133],"offload":[16],"processing":[18],"to":[19,47,74,84,129,139],"dedicated":[21,89],"thread.":[22,91],"The":[23],"central":[24],"premise":[25],"is":[26],"that":[27],"given":[28],"the":[29,37,51,111,130],"rapidly":[30],"increasing":[31],"core":[32],"counts":[33],"on":[34],"modern":[35],"systems,":[36],"improvements":[38],"performance":[41,136],"arising":[42],"from":[43],"dedicating":[44],"thread":[46],"drive":[48],"outweigh":[50],"small":[52],"loss":[53],"of":[54,62,113],"resources":[55],"application":[57,72],"computation,":[58],"particularly":[59],"when":[60],"overlap":[61],"computation":[65],"can":[66],"be":[67,85],"exploited.":[68],"Our":[69,106,124],"allows":[71],"threads":[73],"make":[75],"calls":[77],"concurrently,":[78],"enqueuing":[79],"these":[80],"as":[81],"tasks":[83],"processed":[86],"by":[87],"This":[92],"not":[93],"only":[94],"guarantees":[95],"such":[98],"operations,":[100],"but":[101],"also":[102],"reduces":[103,110],"load":[104],"imbalance.":[105],"implementation":[107],"additionally":[108],"significantly":[109],"overhead":[112],"mutual":[114],"exclusion":[115],"seen":[116],"existing":[118],"implementations":[119],"applications":[121],"using":[122],"MPI_THREAD_MULTIPLE.":[123],"technique":[125],"requires":[126],"no":[127],"modification":[128],"application,":[131],"demonstrate":[134],"significant":[135],"improvement":[137],"(up":[138],"2X)":[140],"QCD,":[142],"1-D":[143],"FFT":[144],"deep":[146],"learning":[147],"CNN":[148],"applications.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}