{"id":"https://openalex.org/W4388581138","doi":"https://doi.org/10.1145/3624062.3624113","title":"OpenSHMEM Queues: An abstraction for enhancing message rate, bandwidth utilization, and reducing tail latency in OpenSHMEM Applications","display_name":"OpenSHMEM Queues: An abstraction for enhancing message rate, bandwidth utilization, and reducing tail latency in OpenSHMEM Applications","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581138","doi":"https://doi.org/10.1145/3624062.3624113"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624113","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624113","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624113","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045160894","display_name":"Vishwanath Venkatesan","orcid":"https://orcid.org/0009-0002-6260-4611"},"institutions":[{"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":["US"],"is_corresponding":true,"raw_author_name":"Vishwanath Venkatesan","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067995943","display_name":"Manjunath Gorentla Venkata","orcid":"https://orcid.org/0000-0002-5282-1682"},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"Manjunath Gorentla Venkata","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045160894"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":0.6151,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64557161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"448","last_page":"457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991000294685364,"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":0.998199999332428,"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":0.8839306831359863},{"id":"https://openalex.org/keywords/message-queue","display_name":"Message queue","score":0.8032630085945129},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.7316107749938965},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.6177619099617004},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.5796216130256653},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.5534025430679321},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5416082143783569},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5190049409866333},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5026974678039551},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.4868239760398865},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.45316237211227417},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.42920926213264465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8839306831359863},{"id":"https://openalex.org/C26324664","wikidata":"https://www.wikidata.org/wiki/Q1065525","display_name":"Message queue","level":2,"score":0.8032630085945129},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.7316107749938965},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.6177619099617004},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.5796216130256653},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5534025430679321},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5416082143783569},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5190049409866333},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5026974678039551},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.4868239760398865},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.45316237211227417},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.42920926213264465},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3624062.3624113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624113","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624113","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3624062.3624113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624113","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624113","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581138.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1955591353","https://openalex.org/W1962931680","https://openalex.org/W1986239736","https://openalex.org/W2012313745","https://openalex.org/W2079577430","https://openalex.org/W2128043278","https://openalex.org/W2180682038","https://openalex.org/W2921963403","https://openalex.org/W2984468687","https://openalex.org/W2985709405","https://openalex.org/W2997804335","https://openalex.org/W4200049724","https://openalex.org/W4206159778"],"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":{"The":[0,43],"performance":[1],"of":[2,17,34,45,94,104,122,232],"OpenSHMEM":[3,50,78,95,169,185,191,216],"applications":[4],"is":[5,113],"significantly":[6],"influenced":[7],"by":[8],"the":[9,14,32,38,49,77,120,168,184],"network":[10,23],"message":[11,27,57,173,195,219],"rate":[12],"and":[13,41,96,145,175,198],"efficient":[15],"utilization":[16],"bandwidth":[18,213],"for":[19,107,115,133,167,178,190,204,240],"small":[20,179],"messages.":[21],"While":[22],"hardware":[24],"offers":[25],"higher":[26],"rates,":[28],"software":[29],"overheads":[30],"hinder":[31],"achievement":[33],"these":[35,158],"rates":[36],"within":[37],"programming":[39,79,170],"model":[40,51],"applications.":[42],"absence":[44],"appropriate":[46],"abstractions":[47],"in":[48,76,119,126,206,227,237],"exacerbates":[52],"this":[53,160],"challenge.":[54],"For":[55],"instance,":[56],"aggregation,":[58],"which":[59],"has":[60],"been":[61],"successful":[62],"with":[63,218,230],"MPI":[64],"derived":[65],"datatypes":[66],"through":[67],"user":[68,143],"mode":[69],"memory":[70],"registration":[71],"(UMR),":[72],"encounters":[73],"abstraction":[74,166],"hurdles":[75],"model.":[80],"Although,":[81],"such":[82],"improvements":[83,231],"can":[84,139,146],"only":[85],"be":[86,98],"achieved":[87,100],"using":[88,215],"separate":[89],"middleware":[90],"built":[91],"on":[92],"top":[93],"cannot":[97],"easily":[99],"natively.":[101],"Furthermore,":[102],"Quality":[103],"Service":[105],"(QoS)":[106],"short":[108],"messages":[109],"under":[110],"high":[111],"loads":[112],"important":[114],"HPC":[116,128],"applications,":[117],"particularly":[118],"case":[121],"OpenSHMEM.":[123,207],"Congestion":[124],"experienced":[125],"shared":[127,134],"systems":[129],"due":[130],"to":[131,152,234],"contention":[132],"networks,":[135],"I/O":[136],"systems,":[137],"etc.,":[138],"create":[140],"an":[141],"adverse":[142],"experience":[144],"impact":[147],"overall":[148],"system":[149],"performance,":[150],"leading":[151],"prolonged":[153],"tail":[154,228],"latencies.":[155],"To":[156],"address":[157],"issues,":[159],"paper":[161],"introduces":[162],"a":[163,188,211,224],"Queues":[164],"API":[165],"model,":[171],"enabling":[172],"aggregation":[174,196],"in-network":[176],"prioritization":[177],"data":[180],"transfers.":[181,242],"We":[182],"present":[183],"API,":[186],"build":[187],"prototype":[189],"queues,":[192],"explore":[193],"various":[194],"techniques,":[197],"evaluate":[199],"NVIDIA":[200],"InfiniBand":[201],"virtual":[202],"lanes":[203],"QoS":[205],"Our":[208],"results":[209],"demonstrate":[210],"2x-3x":[212],"improvement":[214],"queues":[217],"aggregation.":[220],"Additionally,":[221],"we":[222],"achieve":[223],"substantial":[225],"reduction":[226],"latency,":[229],"up":[233],"3.5x":[235],"observed":[236],"congested":[238],"scenarios":[239],"one-sided":[241]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-01-25T23:04:38.658462","created_date":"2025-10-10T00:00:00"}