{"id":"https://openalex.org/W1576599451","doi":"https://doi.org/10.1109/hipc.2014.7116873","title":"Designing efficient small message transfer mechanism for inter-node MPI communication on InfiniBand GPU clusters","display_name":"Designing efficient small message transfer mechanism for inter-node MPI communication on InfiniBand GPU clusters","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1576599451","doi":"https://doi.org/10.1109/hipc.2014.7116873","mag":"1576599451"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2014.7116873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2014.7116873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 21st International Conference on High Performance Computing (HiPC)","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/A5082022175","display_name":"Rongpei Shi","orcid":"https://orcid.org/0000-0002-5007-4249"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rong Shi","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University","Department of Computer Science and Engineering, The Ohio-State University#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio-State University#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055771884","display_name":"Sreeram Potluri","orcid":"https://orcid.org/0000-0001-6420-1635"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreeram Potluri","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University","Department of Computer Science and Engineering, The Ohio-State University#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio-State University#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"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/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khaled Hamidouche","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University","Department of Computer Science and Engineering, The Ohio-State University#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio-State University#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044269704","display_name":"Jonathan Perkins","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Perkins","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University","Department of Computer Science and Engineering, The Ohio-State University#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio-State University#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775673","display_name":"Mingzhe Li","orcid":"https://orcid.org/0000-0002-0883-3678"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingzhe Li","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University","Department of Computer Science and Engineering, The Ohio-State University#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio-State University#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077080471","display_name":"D. Rossetti","orcid":"https://orcid.org/0000-0002-5113-1102"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Davide Rossetti","raw_affiliation_strings":["NVIDIA Corporation","NVIDIA.CORPORATION"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA.CORPORATION","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. D K Panda","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University","Department of Computer Science and Engineering, The Ohio-State University#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio-State University#TAB#","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5082022175"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.8778,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.91139546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9984999895095825,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9968000054359436,"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/T11896","display_name":"Opportunistic and Delay-Tolerant Networks","score":0.9929999709129333,"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":0.9100768566131592},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.8833848237991333},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.7919232249259949},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7130270600318909},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5385689735412598},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5294907689094543},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.4796179234981537},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.4348789155483246},{"id":"https://openalex.org/keywords/message-queue","display_name":"Message queue","score":0.42273640632629395},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.26219266653060913},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.16619393229484558},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1489255130290985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9100768566131592},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.8833848237991333},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.7919232249259949},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7130270600318909},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5385689735412598},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5294907689094543},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.4796179234981537},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.4348789155483246},{"id":"https://openalex.org/C26324664","wikidata":"https://www.wikidata.org/wiki/Q1065525","display_name":"Message queue","level":2,"score":0.42273640632629395},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26219266653060913},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.16619393229484558},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1489255130290985},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipc.2014.7116873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2014.7116873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 21st International Conference on High Performance Computing (HiPC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1637731592","https://openalex.org/W1964981582","https://openalex.org/W1994531540","https://openalex.org/W2005111477","https://openalex.org/W2012173227","https://openalex.org/W2014325923","https://openalex.org/W2024565525","https://openalex.org/W2025388037","https://openalex.org/W2054522323","https://openalex.org/W2063057407","https://openalex.org/W2070940137","https://openalex.org/W2071739952","https://openalex.org/W2073306876","https://openalex.org/W2078391824","https://openalex.org/W2081981740","https://openalex.org/W2087417231","https://openalex.org/W2110813866","https://openalex.org/W2121444153","https://openalex.org/W2150639558","https://openalex.org/W4285719527","https://openalex.org/W6641272004","https://openalex.org/W6648868179","https://openalex.org/W6656741298","https://openalex.org/W6682085584"],"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/W2089636054","https://openalex.org/W2751263050","https://openalex.org/W2107239657"],"abstract_inverted_index":{"Increasing":[0],"number":[1],"of":[2,11,38,174],"MPI":[3,60,99],"applications":[4,32],"are":[5],"being":[6],"ported":[7],"to":[8,24,45,51,67,88,118,130,141,162,182,201,246,257],"take":[9],"advantage":[10],"the":[12,26,36,58,77,102,143,172,179,218,247],"compute":[13],"power":[14],"offered":[15],"by":[16,221],"GPUs.":[17,39],"Data":[18],"movement":[19,93],"on":[20,240],"GPU":[21,49,80,169,187],"clusters":[22],"continues":[23],"be":[25],"major":[27],"bottleneck":[28,70],"that":[29],"keeps":[30],"scientific":[31],"from":[33,48],"fully":[34],"harnessing":[35],"potential":[37],"Earlier,":[40],"GPU-GPU":[41],"inter-node":[42],"communication":[43,188],"has":[44],"move":[46],"data":[47,92,160],"memory":[50,53],"host":[52,167],"before":[54],"sending":[55],"it":[56],"over":[57],"network.":[59],"libraries":[61,100],"like":[62],"MVAPICH2":[63],"have":[64],"provided":[65],"solutions":[66],"alleviate":[68],"this":[69,91,124,177],"using":[71,193],"host-based":[72],"pipelining":[73],"techniques.":[74],"Besides":[75],"that,":[76,244],"newly":[78],"introduced":[79],"Direct":[81],"RDMA":[82],"(GDR)":[83],"is":[84,178],"a":[85,158],"promising":[86],"solution":[87],"further":[89],"solve":[90],"bottleneck.":[94],"However,":[95],"existing":[96,249],"design":[97,231],"in":[98,206,266],"applies":[101],"rendezvous":[103],"protocol":[104,145],"for":[105,113,135,186,189,208,261,269],"all":[106],"message":[107,115,121,137,191],"sizes,":[108,192],"which":[109],"incurs":[110],"considerable":[111],"overhead":[112],"small":[114,136,190],"communications":[116,134],"due":[117],"extra":[119],"synchronization":[120],"exchange.":[122],"In":[123],"paper,":[125],"we":[126,156],"propose":[127,157,183],"new":[128,159],"techniques":[129],"optimize":[131],"internode":[132],"GPU-to-GPU":[133,209],"sizes.":[138],"Our":[139,196],"designs":[140,185,216,254],"support":[142,148],"eager":[144,194],"include":[146],"efficient":[147,184],"at":[149],"both":[150],"sender":[151],"and":[152,168,203,210,223,236,263],"receiver":[153],"sides.":[154],"Furthermore,":[155],"path":[161],"provide":[163],"fast":[164],"copies":[165],"between":[166],"memories.":[170],"To":[171],"best":[173,248],"our":[175,229,252],"knowledge,":[176],"first":[180],"study":[181],"protocol.":[195],"experimental":[197],"results":[198],"demonstrate":[199],"up":[200,256],"59%":[202],"63%":[204],"reduction":[205,260],"latency":[207,259],"CPU-to-GPU":[211],"point-to-point":[212],"communications,":[213],"respectively.":[214,225,271],"These":[215],"boost":[217],"uni-directional":[219],"bandwidth":[220],"7.3x":[222],"1.7x,":[224],"We":[226],"also":[227],"evaluate":[228],"proposed":[230,253],"with":[232],"two":[233],"end-applications:":[234],"GPULBM":[235,262],"HOOMD-blue.":[237],"Performance":[238],"numbers":[239],"Kepler":[241],"GPUs":[242],"shows":[243],"compared":[245],"GDR":[250],"design,":[251],"achieve":[255],"23.4%":[258],"58%":[264],"increase":[265],"average":[267],"TPS":[268],"HOOMD-blue,":[270]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}