{"id":"https://openalex.org/W4414898606","doi":"https://doi.org/10.1109/cluster59342.2025.11186498","title":"Uniconn: A Uniform High-Level Communication Library for Portable Multi-GPU Programming","display_name":"Uniconn: A Uniform High-Level Communication Library for Portable Multi-GPU Programming","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4414898606","doi":"https://doi.org/10.1109/cluster59342.2025.11186498"},"language":"en","primary_location":{"id":"doi:10.1109/cluster59342.2025.11186498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5092212134","display_name":"Do\u011fan Sa\u011fbili","orcid":"https://orcid.org/0000-0002-9603-2466"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Do\u011fan Sa\u011fbili","raw_affiliation_strings":["Koç University,Department of Computer Science and Engineering,Istanbul,Turkiye"],"affiliations":[{"raw_affiliation_string":"Koç University,Department of Computer Science and Engineering,Istanbul,Turkiye","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119879249","display_name":"Sinan Ekmek\u00e7iba\u015f\u0131","orcid":"https://orcid.org/0009-0003-5377-6339"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Sinan Ekmek\u00e7iba\u015f\u0131","raw_affiliation_strings":["Koç University,Department of Computer Science and Engineering,Istanbul,Turkiye"],"affiliations":[{"raw_affiliation_string":"Koç University,Department of Computer Science and Engineering,Istanbul,Turkiye","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062016419","display_name":"Khaled Z. Ibrahim","orcid":"https://orcid.org/0009-0004-5362-3612"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khaled Z. Ibrahim","raw_affiliation_strings":["Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory,CA,USA"],"affiliations":[{"raw_affiliation_string":"Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory,CA,USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399125","display_name":"Tan Nguyen","orcid":"https://orcid.org/0000-0003-3748-403X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tan Nguyen","raw_affiliation_strings":["Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory,CA,USA"],"affiliations":[{"raw_affiliation_string":"Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory,CA,USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040713791","display_name":"Didem Unat","orcid":"https://orcid.org/0000-0002-2351-0770"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Didem Unat","raw_affiliation_strings":["Koç University,Department of Computer Science and Engineering,Istanbul,Turkiye"],"affiliations":[{"raw_affiliation_string":"Koç University,Department of Computer Science and Engineering,Istanbul,Turkiye","institution_ids":["https://openalex.org/I1351752"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092212134"],"corresponding_institution_ids":["https://openalex.org/I1351752"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29386237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9550999999046326,"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":0.9550999999046326,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9343000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6194000244140625},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6087999939918518},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.532800018787384},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.4950999915599823},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.44020000100135803},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.43959999084472656},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.43149998784065247},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.400299996137619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345999717712402},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6087999939918518},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.532800018787384},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.400299996137619},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3797000050544739},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C3019612716","wikidata":"https://www.wikidata.org/wiki/Q730920","display_name":"Problem solver","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster59342.2025.11186498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4142194600","display_name":null,"funder_award_id":"EHPC-DEV-2024D10-091","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"}],"funders":[{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1962931680","https://openalex.org/W1964981582","https://openalex.org/W2035080386","https://openalex.org/W2913752846","https://openalex.org/W2944412207","https://openalex.org/W2998812396","https://openalex.org/W3043803354","https://openalex.org/W3046421657","https://openalex.org/W3122949375","https://openalex.org/W3166649773","https://openalex.org/W3170377433","https://openalex.org/W3173970356","https://openalex.org/W3195293013","https://openalex.org/W4313408245","https://openalex.org/W4362566357","https://openalex.org/W4381327256","https://openalex.org/W4384705436","https://openalex.org/W4399845821","https://openalex.org/W4402702025","https://openalex.org/W4406157504","https://openalex.org/W4406163815"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"HPC":[1],"and":[2,17,32,40,46,54,93,105,122,125,135,151,173],"AI":[3],"systems":[4],"increasingly":[5],"rely":[6],"on":[7,153],"multi-GPU":[8],"clusters,":[9],"where":[10],"communication":[11,87],"libraries":[12,26],"such":[13],"as":[14],"MPI,":[15,149],"NCCL/RCCL,":[16,150],"NVSHMEM":[18,152],"enable":[19],"data":[20],"movement":[21],"across":[22,52,96],"GPUs.":[23,157],"While":[24],"these":[25],"are":[27],"widely":[28],"used":[29],"in":[30],"frameworks":[31],"solver":[33,172],"packages,":[34],"their":[35],"distinct":[36],"APIs,":[37],"synchronization":[38],"models,":[39],"integration":[41],"mechanisms":[42],"introduce":[43],"programming":[44],"complexity":[45],"limit":[47],"portability.":[48],"Performance":[49],"also":[50],"varies":[51],"workloads":[53],"system":[55],"architectures,":[56],"making":[57],"it":[58],"difficult":[59],"to":[60,70,115,155],"achieve":[61],"consistent":[62],"efficiency.":[63],"These":[64],"issues":[65],"present":[66,80],"a":[67,82,132,136],"significant":[68],"obstacle":[69],"writing":[71],"portable,":[72],"high-performance":[73],"code":[74],"for":[75,169,176],"large-scale":[76],"GPU":[77,97],"systems.":[78],"We":[79,118],"Uniconn,":[81],"unified,":[83],"portable":[84],"high-level":[85],"C++":[86],"library":[88],"that":[89],"supports":[90],"both":[91],"point-to-point":[92],"collective":[94],"operations":[95],"clusters.":[98],"Uniconn":[99,161],"enables":[100],"seamless":[101],"switching":[102],"between":[103],"backends":[104],"APIs":[106],"(host":[107],"or":[108,112],"device)":[109],"with":[110],"minimal":[111],"no":[113],"changes":[114],"application":[116],"code.":[117],"describe":[119],"its":[120,127],"design":[121],"core":[123],"constructs,":[124],"evaluate":[126],"performance":[128],"using":[129],"network":[130],"benchmarks,":[131],"Jacobi":[133,171],"solver,":[134],"Conjugate":[137,178],"Gradient":[138,179],"solver.":[139,180],"Across":[140],"three":[141],"supercomputers,":[142],"we":[143],"compare":[144],"Uniconn's":[145],"overhead":[146],"against":[147],"CUDA/ROCm-aware":[148],"up":[154],"64":[156],"In":[158],"most":[159],"cases,":[160],"incurs":[162],"negligible":[163],"overhead,":[164],"typically":[165],"under":[166,174],"1":[167],"%":[168],"the":[170,177],"2%":[175]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}