{"id":"https://openalex.org/W2767210925","doi":"https://doi.org/10.1145/3126908.3126950","title":"GPU triggered networking for intra-kernel communications","display_name":"GPU triggered networking for intra-kernel communications","publication_year":2017,"publication_date":"2017-11-08","ids":{"openalex":"https://openalex.org/W2767210925","doi":"https://doi.org/10.1145/3126908.3126950","mag":"2767210925"},"language":"en","primary_location":{"id":"doi:10.1145/3126908.3126950","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126908.3126950","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005659585","display_name":"Michael LeBeane","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael LeBeane","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048039700","display_name":"Khaled Hamidouche","orcid":"https://orcid.org/0000-0003-4836-5335"},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Khaled Hamidouche","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009103835","display_name":"Brad Benton","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brad Benton","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021886781","display_name":"Maur\u00edcio Breternitz","orcid":"https://orcid.org/0000-0003-1752-6255"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mauricio Breternitz","raw_affiliation_strings":["Instituto Universitario de Lisboa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Universitario de Lisboa","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109010789","display_name":"Steven K. Reinhardt","orcid":"https://orcid.org/0000-0002-2479-0030"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Steven K. Reinhardt","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068885069","display_name":"Lizy K. John","orcid":"https://orcid.org/0000-0002-8747-5214"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lizy K. John","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5433,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91248273,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"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":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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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":0.8716734051704407},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7318644523620605},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.662927508354187},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6235819458961487},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.4682658016681671},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.46717721223831177},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.43816953897476196},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.427802175283432},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4268009662628174},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.3711753487586975},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3608296811580658},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3312017321586609},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26372939348220825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8716734051704407},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7318644523620605},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.662927508354187},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6235819458961487},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.4682658016681671},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.46717721223831177},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.43816953897476196},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.427802175283432},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4268009662628174},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.3711753487586975},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3608296811580658},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3312017321586609},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26372939348220825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3126908.3126950","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126908.3126950","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3390915338","display_name":null,"funder_award_id":"1337393","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1446278828","https://openalex.org/W1480281982","https://openalex.org/W1575350781","https://openalex.org/W1590013973","https://openalex.org/W1988756252","https://openalex.org/W1996488762","https://openalex.org/W2006312753","https://openalex.org/W2054522323","https://openalex.org/W2062964224","https://openalex.org/W2087417231","https://openalex.org/W2109039688","https://openalex.org/W2121444153","https://openalex.org/W2147657366","https://openalex.org/W2150618958","https://openalex.org/W2398969933","https://openalex.org/W2402285027","https://openalex.org/W2488497244","https://openalex.org/W2557367833","https://openalex.org/W2591333772","https://openalex.org/W2730016893","https://openalex.org/W4205140131"],"related_works":["https://openalex.org/W2056717482","https://openalex.org/W2030707850","https://openalex.org/W2020279179","https://openalex.org/W2170611190","https://openalex.org/W2566934642","https://openalex.org/W2324262650","https://openalex.org/W2548246577","https://openalex.org/W2092007952","https://openalex.org/W2096672917","https://openalex.org/W2019821619"],"abstract_inverted_index":{"GPUs":[0,20,39],"are":[1],"widespread":[2],"across":[3,21],"clusters":[4],"of":[5,34],"compute":[6],"nodes":[7],"due":[8],"to":[9,28,40,59],"their":[10],"attractive":[11],"performance":[12,49],"for":[13],"data":[14],"parallel":[15],"codes.":[16],"However,":[17],"communicating":[18],"between":[19],"the":[22,44],"cluster":[23],"is":[24],"cumbersome":[25],"when":[26],"compared":[27],"CPU":[29,53],"networking":[30],"implementations.":[31],"A":[32],"number":[33],"recent":[35],"works":[36],"have":[37],"enabled":[38],"more":[41],"naturally":[42],"access":[43],"network,":[45],"but":[46],"suffer":[47],"from":[48],"problems,":[50],"require":[51],"hidden":[52],"helper":[54],"threads,":[55],"or":[56],"restrict":[57],"communications":[58],"kernel":[60],"boundaries.":[61]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}