{"id":"https://openalex.org/W4417403284","doi":"https://doi.org/10.1109/pact65351.2025.00041","title":"GPU Stream-Aware Communication for Effective Pipelining","display_name":"GPU Stream-Aware Communication for Effective Pipelining","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4417403284","doi":"https://doi.org/10.1109/pact65351.2025.00041"},"language":null,"primary_location":{"id":"doi:10.1109/pact65351.2025.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact65351.2025.00041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th International Conference on Parallel Architectures and Compilation Techniques (PACT)","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/A5030212303","display_name":"Naveen Namashivayam","orcid":null},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Naveen Namashivayam","raw_affiliation_strings":["University of Minnesota,USA"],"affiliations":[{"raw_affiliation_string":"University of Minnesota,USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010923189","display_name":"Krishna Kandalla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Kandalla","raw_affiliation_strings":["Hewlett Packard Enterprise,USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise,USA","institution_ids":["https://openalex.org/I4210122178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052005800","display_name":"Pen-Chung Yew","orcid":"https://orcid.org/0000-0001-9653-8777"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pen-Chung Yew","raw_affiliation_strings":["University of Minnesota,USA"],"affiliations":[{"raw_affiliation_string":"University of Minnesota,USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087537904","display_name":"Trey White","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trey White","raw_affiliation_strings":["Hewlett Packard Enterprise,USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise,USA","institution_ids":["https://openalex.org/I4210122178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013389843","display_name":"Larry Kaplan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Larry Kaplan","raw_affiliation_strings":["Hewlett Packard Enterprise,USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise,USA","institution_ids":["https://openalex.org/I4210122178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103043312","display_name":"Mark D. Pagel","orcid":"https://orcid.org/0000-0002-8109-3995"},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Pagel","raw_affiliation_strings":["Hewlett Packard Enterprise,USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise,USA","institution_ids":["https://openalex.org/I4210122178"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030212303"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46733241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"372","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8496999740600586,"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":0.8496999740600586,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.057100001722574234,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.025200000032782555,"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/synchronization","display_name":"Synchronization (alternating current)","score":0.656499981880188},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5554999709129333},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.48559999465942383},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.48010000586509705},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4666000008583069},{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.46050000190734863},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3828999996185303},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.36809998750686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8641999959945679},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.656499981880188},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.48559999465942383},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44530001282691956},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.36809998750686646},{"id":"https://openalex.org/C103987645","wikidata":"https://www.wikidata.org/wiki/Q985806","display_name":"Network interface","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C108734733","wikidata":"https://www.wikidata.org/wiki/Q1172333","display_name":"Data synchronization","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C12269588","wikidata":"https://www.wikidata.org/wiki/Q132364","display_name":"Communications protocol","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pact65351.2025.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact65351.2025.00041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th International Conference on Parallel Architectures and Compilation Techniques (PACT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W106662895","https://openalex.org/W165519999","https://openalex.org/W1902879054","https://openalex.org/W1929619420","https://openalex.org/W1964981582","https://openalex.org/W2024565525","https://openalex.org/W2025388037","https://openalex.org/W2030338727","https://openalex.org/W2054522323","https://openalex.org/W2070940137","https://openalex.org/W2093337950","https://openalex.org/W2094526959","https://openalex.org/W2099020156","https://openalex.org/W2109039688","https://openalex.org/W2126403791","https://openalex.org/W2207785195","https://openalex.org/W2402285027","https://openalex.org/W2481316611","https://openalex.org/W2560542919","https://openalex.org/W2730016893","https://openalex.org/W2886651213","https://openalex.org/W2917086405","https://openalex.org/W2938171278","https://openalex.org/W2948254258","https://openalex.org/W2994302756","https://openalex.org/W2995761656","https://openalex.org/W3037022899","https://openalex.org/W3046421657","https://openalex.org/W3129251660","https://openalex.org/W3198396876","https://openalex.org/W4205627056","https://openalex.org/W4231564937","https://openalex.org/W4245970586","https://openalex.org/W4294008856"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"heterogeneous":[1],"supercomputing":[2],"systems":[3],"consist":[4],"of":[5,114],"CPUs,":[6],"GPUs,":[7],"and":[8,46,48,76,128,142,147,152],"high-speed":[9],"network":[10],"interconnects.":[11],"Communication":[12],"libraries":[13],"that":[14],"support":[15],"efficient":[16],"inter-process":[17],"data":[18,35,77],"movement":[19,78],"between":[20,43,125],"memory":[21],"buffers,":[22],"especially":[23],"those":[24],"involving":[25],"GPU":[26],"memory,":[27],"typically":[28],"require":[29],"the":[30,34,44,74,81,84,100,115],"CPU":[31,45,82],"to":[32,72,83,98,109,136],"orchestrate":[33],"transfer":[36],"operations.":[37],"This":[38],"approach":[39],"necessitates":[40],"expensive":[41],"synchronization":[42,75],"GPU,":[47],"is":[49,70,96],"ineffective":[50],"for":[51],"achieving":[52],"better":[53],"compute/communication":[54],"overlap":[55],"in":[56],"applications":[57],"using":[58],"techniques":[59],"like":[60],"pipelining.":[61],"A":[62,86,103],"new":[63],"offload-friendly":[64],"communication":[65,149],"strategy,":[66],"stream-triggered":[67],"(ST)":[68],"communication,":[69],"explored":[71],"offload":[73],"operations":[79],"from":[80],"GPU.":[85],"Message":[87],"Passing":[88],"Interface":[89],"(MPI)":[90],"one-sided":[91],"active":[92,139],"target":[93],"synchronization-based":[94],"implementation":[95,119],"used":[97,108],"illustrate":[99],"proposed":[101],"strategy.":[102],"latency-sensitive":[104],"nearest-neighbor":[105],"microbenchmark":[106],"was":[107],"examine":[110],"various":[111],"performance":[112,122],"characteristics":[113],"implementation.":[116],"The":[117],"offloaded":[118],"showed":[120],"significant":[121],"improvements":[123],"both":[124],"nodes":[126],"(inter-node)":[127],"within":[129],"a":[130],"single":[131],"node":[132],"(intranode)":[133],"when":[134],"compared":[135],"standard":[137],"MPI":[138],"RMA":[140],"(33%":[141],"$\\mathbf{2":[143],"7":[144],"\\%}$,":[145],"respectively)":[146],"point-to-point":[148],"($\\mathbf{9":[150],"\\%}$":[151],"38%,":[153],"respectively).":[154]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-16T00:00:00"}