{"id":"https://openalex.org/W1189273455","doi":"https://doi.org/10.1177/1094342015588142","title":"InfiniBand Verbs on GPU: a case study of controlling an InfiniBand network device from the GPU","display_name":"InfiniBand Verbs on GPU: a case study of controlling an InfiniBand network device from the GPU","publication_year":2015,"publication_date":"2015-06-25","ids":{"openalex":"https://openalex.org/W1189273455","doi":"https://doi.org/10.1177/1094342015588142","mag":"1189273455"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015588142","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015588142","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-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/A5011121841","display_name":"Lena Oden","orcid":"https://orcid.org/0000-0002-9670-5296"},"institutions":[{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer Society","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"funder","lineage":["https://openalex.org/I4923324"]},{"id":"https://openalex.org/I3019415892","display_name":"Fraunhofer Institute for Industrial Mathematics","ror":"https://ror.org/019hjw009","country_code":"DE","type":"facility","lineage":["https://openalex.org/I3019415892","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lena Oden","raw_affiliation_strings":["Competence Center High Performance Computing, Fraunhofer Institute for Industrial Mathematics, Kaisersautern, Germany","1Competence Center High Performance Computing, Fraunhofer Institute for Industrial Mathematics, Kaisersautern, Germany"],"affiliations":[{"raw_affiliation_string":"Competence Center High Performance Computing, Fraunhofer Institute for Industrial Mathematics, Kaisersautern, Germany","institution_ids":["https://openalex.org/I3019415892"]},{"raw_affiliation_string":"1Competence Center High Performance Computing, Fraunhofer Institute for Industrial Mathematics, Kaisersautern, Germany","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014251134","display_name":"Holger Fr\u00f6ning","orcid":"https://orcid.org/0000-0001-9562-0680"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Holger Fr\u00f6ning","raw_affiliation_strings":["Institute of Computer Engineering, Ruprecht-Karls University of Heidelberg, Mannheim, Germany","2Institute of Computer Engineering, Ruprecht-Karls University of Heidelberg, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Engineering, Ruprecht-Karls University of Heidelberg, Mannheim, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"2Institute of Computer Engineering, Ruprecht-Karls University of Heidelberg, Mannheim, Germany","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011121841"],"corresponding_institution_ids":["https://openalex.org/I3019415892","https://openalex.org/I4923324"],"apc_list":null,"apc_paid":null,"fwci":2.4702,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90634087,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"31","issue":"4","first_page":"274","last_page":"284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9973000288009644,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9973000288009644,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9970999956130981,"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/T11478","display_name":"Caching and Content Delivery","score":0.9958000183105469,"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/infiniband","display_name":"InfiniBand","score":0.9887229204177856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8990269899368286},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5993502736091614},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.49875807762145996},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43406838178634644},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4318602681159973},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4282871186733246},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42283371090888977},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.17221099138259888}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.9887229204177856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8990269899368286},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5993502736091614},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.49875807762145996},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43406838178634644},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4318602681159973},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4282871186733246},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42283371090888977},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.17221099138259888}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1177/1094342015588142","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015588142","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:juser.fz-juelich.de:838381","is_oa":false,"landing_page_url":"http://juser.fz-juelich.de/search?p=id:%22FZJ-2017-06993%22","pdf_url":null,"source":{"id":"https://openalex.org/S4306401090","display_name":"JuSER (Forschungszentrum J\u00fclich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I171892758","host_organization_name":"Forschungszentrum J\u00fclich","host_organization_lineage":["https://openalex.org/I171892758"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE (2014). doi:10.1109/IPDPSW.2014.111","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:juser.fz-juelich.de:838385","is_oa":false,"landing_page_url":"http://juser.fz-juelich.de/search?p=id:%22FZJ-2017-06997%22","pdf_url":null,"source":{"id":"https://openalex.org/S4306401090","display_name":"JuSER (Forschungszentrum J\u00fclich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I171892758","host_organization_name":"Forschungszentrum J\u00fclich","host_organization_lineage":["https://openalex.org/I171892758"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The international journal of high performance computing applications 31(4), 274 - 284 (2017). doi:10.1177/1094342015588142","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/242294","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/242294","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"journal article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1586422308","https://openalex.org/W1964479544","https://openalex.org/W1964981582","https://openalex.org/W1968188490","https://openalex.org/W1974211642","https://openalex.org/W1988455636","https://openalex.org/W1988756252","https://openalex.org/W2024565525","https://openalex.org/W2035552916","https://openalex.org/W2070940137","https://openalex.org/W2121444153","https://openalex.org/W2121504627","https://openalex.org/W2398736067","https://openalex.org/W2500725557"],"related_works":["https://openalex.org/W1978254186","https://openalex.org/W4245217724","https://openalex.org/W4390917331","https://openalex.org/W1984788566","https://openalex.org/W4253931064","https://openalex.org/W3166154920","https://openalex.org/W2154082760","https://openalex.org/W1964981582","https://openalex.org/W4282599985","https://openalex.org/W2139382794"],"abstract_inverted_index":{"Due":[0],"to":[1,46,87,100,125,129,135,192,198],"their":[2],"massive":[3,186,215],"parallelism":[4],"and":[5,18,29,63,89,112,117,138,173,190,200],"high":[6,13],"performance":[7,226],"per":[8],"Watt,":[9],"GPUs":[10,75,86,116],"have":[11],"gained":[12],"popularity":[14],"in":[15,32,122,217],"high-performance":[16],"computing":[17],"are":[19,159],"a":[20,36,48,51,70,94,123,202,214],"strong":[21],"candidate":[22],"for":[23,61,177],"future":[24],"exascale":[25],"systems.":[26],"But":[27],"communication":[28,72,140,203],"data":[30],"transfer":[31],"GPU-accelerated":[33],"systems":[34],"remain":[35],"challenging":[37],"problem.":[38],"Since":[39],"the":[40,57,64,67,118,127,146,178,206,210,218,221],"GPU":[41,58,128,207],"normally":[42],"is":[43,54,59,98,174,196],"not":[44,175],"able":[45],"control":[47,83,101,130],"network":[49,120,133],"device,":[50],"hybrid-programming":[52],"model":[53,182],"preferred":[55],"whereby":[56],"used":[60],"calculation":[62],"CPU":[65,96],"handles":[66],"communication.":[68,103],"As":[69],"result,":[71],"between":[73],"distributed":[74],"suffers":[76],"from":[77,85],"unnecessary":[78],"overhead,":[79],"introduced":[80],"by":[81,162],"switching":[82],"flow":[84],"CPUs":[88],"vice":[90],"versa.":[91],"Furthermore,":[92],"often":[93],"designated":[95],"thread":[97],"required":[99,197],"GPU-related":[102],"In":[104],"this":[105],"work,":[106],"we":[107],"modify":[108],"user":[109],"space":[110],"libraries":[111],"device":[113,121,134],"drivers":[114],"of":[115,145,166,183,188,220],"InfiniBand":[119,132,157,222],"way":[124],"enable":[126],"an":[131],"independently":[136],"source":[137,199],"sink":[139,201],"requests":[141],"without":[142],"any":[143],"involvement":[144],"CPU.":[147],"Our":[148],"results":[149],"show":[150],"that":[151,195],"complex":[152],"networking":[153],"protocols":[154],"such":[155],"as":[156],"Verbs":[158],"better":[160],"handled":[161],"CPUs,":[163],"since":[164],"overhead":[165],"work":[167],"request":[168,204],"generation":[169],"cannot":[170],"be":[171,228],"parallelized":[172],"suitable":[176],"highly":[179],"parallel":[180],"programming":[181],"GPUs.":[184],"The":[185],"number":[187],"instructions":[189],"accesses":[191],"host":[193],"memory":[194],"on":[205],"slows":[208],"down":[209],"performance.":[211],"Only":[212],"through":[213],"reduction":[216],"complexity":[219],"protocol":[223],"can":[224],"some":[225],"improvements":[227],"achieved.":[229]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"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"}