{"id":"https://openalex.org/W2296046349","doi":"https://doi.org/10.1145/2832241.2832247","title":"Hyper-Q aware intranode MPI collectives on the GPU","display_name":"Hyper-Q aware intranode MPI collectives on the GPU","publication_year":2015,"publication_date":"2015-11-09","ids":{"openalex":"https://openalex.org/W2296046349","doi":"https://doi.org/10.1145/2832241.2832247","mag":"2296046349"},"language":"en","primary_location":{"id":"doi:10.1145/2832241.2832247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2832241.2832247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Workshop on Extreme Scale Programming Models and Middleware","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/A5080002194","display_name":"Iman Faraji","orcid":"https://orcid.org/0000-0001-9442-7424"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Iman Faraji","raw_affiliation_strings":["Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039854005","display_name":"Ahmad Afsahi","orcid":"https://orcid.org/0000-0002-2924-6851"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmad Afsahi","raw_affiliation_strings":["Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080002194"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":0.6656,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76126267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9973999857902527,"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":0.9973999857902527,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9947999715805054,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9912999868392944,"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":0.8967597484588623},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8385015726089478},{"id":"https://openalex.org/keywords/inter-process-communication","display_name":"Inter-process communication","score":0.7471159100532532},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6651971340179443},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6526315212249756},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6178943514823914},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.5114561319351196},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5020802021026611},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4803161025047302},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.46019983291625977},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44542187452316284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4295567274093628},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4280489385128021},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24433943629264832}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8967597484588623},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8385015726089478},{"id":"https://openalex.org/C204156049","wikidata":"https://www.wikidata.org/wiki/Q751436","display_name":"Inter-process communication","level":2,"score":0.7471159100532532},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6651971340179443},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6526315212249756},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6178943514823914},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5114561319351196},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5020802021026611},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4803161025047302},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.46019983291625977},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44542187452316284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4295567274093628},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4280489385128021},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24433943629264832},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2832241.2832247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2832241.2832247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Workshop on Extreme Scale Programming Models and Middleware","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":5,"referenced_works":["https://openalex.org/W1576599451","https://openalex.org/W1637731592","https://openalex.org/W1987274898","https://openalex.org/W2110813866","https://openalex.org/W2282413880"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"In":[0,79],"GPU":[1,4,23,41,55,92],"clusters,":[2],"high":[3],"utilization":[5],"and":[6,42,56,100,146,159,184,201,215,218,223,230,256],"efficient":[7,125],"communication":[8],"play":[9],"an":[10],"important":[11],"role":[12],"in":[13],"the":[14,17,22,28,34,40,54,62,84,87,91,95,108,133,166,169,182,189,198,204,213,228,233,240,246],"performance":[15],"of":[16,86,135,181,192,203,210,227,232,252],"MPI":[18,156],"applications.":[19],"To":[20,138],"improve":[21],"utilization,":[24],"NVIDIA":[25],"has":[26],"introduced":[27],"Multi":[29],"Process":[30],"Service":[31],"(MPS),":[32],"eliminating":[33],"context-switching":[35],"overhead":[36],"among":[37],"processes":[38,46],"accessing":[39],"allowing":[43],"multiple":[44,114],"intranode":[45,155],"to":[47,66,130,153],"further":[48,131],"overlap":[49],"their":[50,193],"CUDA":[51,98,185],"tasks":[52],"on":[53,90,97,113],"potentially":[57],"share":[58],"its":[59],"resources":[60],"through":[61],"Hyper-Q":[63,68,216],"feature.":[64],"Prior":[65],"MPS,":[67],"could":[69],"only":[70],"provide":[71,104,165,219],"such":[72],"resource":[73],"sharing":[74],"within":[75],"a":[76,143,161,179],"single":[77],"process.":[78],"this":[80,136,139],"paper,":[81],"we":[82,122,141,164],"evaluate":[83],"effect":[85],"MPS":[88,109,214],"service":[89,110],"communications":[93,116,191],"with":[94,245],"focus":[96],"IPC":[99,186],"host-staged":[101,183],"copies.":[102],"We":[103],"evidence":[105],"that":[106,124,149,239],"utilizing":[107],"is":[111,243,250],"beneficial":[112],"interprocess":[115,190],"using":[117],"these":[118],"copy":[119],"types.":[120],"However,":[121],"show":[123],"design":[126],"decisions":[127],"are":[128,208],"required":[129],"harness":[132],"potential":[134],"service.":[137],"aim,":[140],"propose":[142],"Static":[144,247],"algorithm":[145,148,242],"Dynamic":[147,241],"can":[150,258],"be":[151,259],"applied":[152],"various":[154],"collective":[157,194],"operations,":[158],"as":[160],"test":[162],"case":[163],"results":[167,237],"for":[168,188,225],"MPI_Allreduce":[170],"operation.":[171],"Both":[172],"approaches,":[173],"while":[174,249],"following":[175],"different":[176],"algorithms,":[177],"use":[178],"combination":[180],"copies":[187],"designs.":[195],"By":[196],"selecting":[197],"right":[199],"number":[200],"type":[202],"copies,":[205],"our":[206],"algorithms":[207],"capable":[209],"efficiently":[211],"leveraging":[212],"feature":[217],"improvement":[220],"over":[221],"MVAPICH2":[222],"MVAPICH2-GDR":[224],"most":[226],"medium":[229],"all":[231],"large":[234],"messages.":[235],"Our":[236],"suggest":[238],"comparable":[244],"algorithm,":[248],"independent":[251],"any":[253],"tuning":[254],"table":[255],"thus":[257],"portable":[260],"across":[261],"platforms.":[262]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
