{"id":"https://openalex.org/W4316252457","doi":"https://doi.org/10.1145/3547276.3548524","title":"Designing Hierarchical Multi-HCA Aware Allgather in MPI","display_name":"Designing Hierarchical Multi-HCA Aware Allgather in MPI","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4316252457","doi":"https://doi.org/10.1145/3547276.3548524"},"language":"en","primary_location":{"id":"doi:10.1145/3547276.3548524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3547276.3548524","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548524","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548524","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049257402","display_name":"Tu Tran","orcid":"https://orcid.org/0000-0003-0040-8404"},"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":"Tu Tran","raw_affiliation_strings":["The Ohio State University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004702010","display_name":"B Micha\u0142owicz","orcid":"https://orcid.org/0000-0002-7450-5787"},"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":"Benjamin Michalowicz","raw_affiliation_strings":["The Ohio State University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103171233","display_name":"Bharath Ramesh","orcid":"https://orcid.org/0000-0002-6430-8587"},"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":"Bharath Ramesh","raw_affiliation_strings":["The Ohio State University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"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":"Hari Subramoni","raw_affiliation_strings":["The Ohio State University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078128277","display_name":"Aamir Shafi","orcid":"https://orcid.org/0000-0002-1924-2769"},"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":"Aamir Shafi","raw_affiliation_strings":["The Ohio State University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"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. Panda","raw_affiliation_strings":["The Ohio State University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.539,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60429417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998999834060669,"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":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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/adapter","display_name":"Adapter (computing)","score":0.8566476106643677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8087031841278076},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.7032157778739929},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.6909404397010803},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6513856053352356},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6058616638183594},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.49834227561950684},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.48369914293289185},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.48161691427230835},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4720804691314697},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.45579230785369873},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4496335983276367},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43838199973106384},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07784044742584229}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.8566476106643677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087031841278076},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.7032157778739929},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.6909404397010803},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6513856053352356},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6058616638183594},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.49834227561950684},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.48369914293289185},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.48161691427230835},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4720804691314697},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.45579230785369873},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4496335983276367},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43838199973106384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07784044742584229},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3547276.3548524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3547276.3548524","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548524","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3547276.3548524","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3547276.3548524","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548524","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G202197749","display_name":"Computation for the Endless Frontier","funder_award_id":"1818253","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3746232255","display_name":null,"funder_award_id":"NCR-130002","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4196433103","display_name":"OAC Core: Small: Next-Generation Communication and I/O Middleware for HPC and Deep Learning with Smart NICs","funder_award_id":"2007991","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5271487896","display_name":"Operations & Maintenance for the Endless Frontier","funder_award_id":"1854828","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5279863110","display_name":"Collaborative Research: Frameworks: Designing Next-Generation MPI Libraries for Emerging Dense GPU Systems","funder_award_id":"1931537","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8585293727","display_name":"MRI: RADiCAL: Reconfigurable Major Research Cyberinfrastructure for Advanced Computational Data Analytics and Machine Learning","funder_award_id":"2018627","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4316252457.pdf","grobid_xml":"https://content.openalex.org/works/W4316252457.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1498011047","https://openalex.org/W1672316377","https://openalex.org/W2012313745","https://openalex.org/W2057332538","https://openalex.org/W2085040216","https://openalex.org/W2100525661","https://openalex.org/W2109349370","https://openalex.org/W2111580991","https://openalex.org/W2131613942","https://openalex.org/W2133695315","https://openalex.org/W2136434791","https://openalex.org/W2139702875","https://openalex.org/W2513383847","https://openalex.org/W2609332365","https://openalex.org/W2617739603","https://openalex.org/W2758990545","https://openalex.org/W2885707392","https://openalex.org/W2886520239","https://openalex.org/W2899266172","https://openalex.org/W2970971581","https://openalex.org/W2985025837","https://openalex.org/W3096262771","https://openalex.org/W3209029431","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W4386915331","https://openalex.org/W2124048060","https://openalex.org/W2378910916","https://openalex.org/W1511717675","https://openalex.org/W2361929291","https://openalex.org/W2116006827","https://openalex.org/W2086666199","https://openalex.org/W2185992486","https://openalex.org/W2110637160","https://openalex.org/W1965374499"],"abstract_inverted_index":{"To":[0],"accelerate":[1],"the":[2,27,35],"communication":[3],"between":[4],"nodes,":[5],"supercomputers":[6],"are":[7],"now":[8],"equipped":[9],"with":[10,90],"multiple":[11],"network":[12],"adapters":[13,31,45],"per":[14,32,46],"node,":[15],"resulting":[16],"in":[17,92,97],"a":[18,57,71,98],"\u201dmulti-rail\u201d":[19],"network.":[20],"The":[21,65],"second":[22],"and":[23,85,94],"third-placed":[24],"systems":[25],"of":[26,52,63],"Top500":[28],"use":[29],"two":[30],"node;":[33],"recently,":[34],"ThetaGPU":[36],"system":[37],"at":[38],"Argonne":[39],"National":[40],"Laboratory":[41],"(ANL)":[42],"uses":[43],"eight":[44],"node.":[47],"With":[48],"such":[49],"an":[50],"availability":[51],"networking":[53],"resources,":[54,84],"it":[55],"is":[56,70],"non-trivial":[58],"task":[59],"to":[60],"utilize":[61,82],"all":[62,79,83],"them.":[64],"Message":[66],"Passing":[67],"Interface":[68],"(MPI)":[69],"dominant":[72],"model":[73],"for":[74],"high-performance":[75],"computing":[76],"clusters.":[77],"Not":[78],"MPI":[80],"collectives":[81],"this":[86],"becomes":[87],"more":[88],"apparent":[89],"advances":[91],"bandwidth":[93],"adapter":[95],"count":[96],"given":[99],"cluster.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}