{"id":"https://openalex.org/W4409133378","doi":"https://doi.org/10.1109/hpec62836.2024.10938430","title":"A Performance Analysis of GPU-Aware MPI Implementations Over the Slingshot-11 Interconnect","display_name":"A Performance Analysis of GPU-Aware MPI Implementations Over the Slingshot-11 Interconnect","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4409133378","doi":"https://doi.org/10.1109/hpec62836.2024.10938430"},"language":"en","primary_location":{"id":"doi:10.1109/hpec62836.2024.10938430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5074560418","display_name":"Michael Beebe","orcid":"https://orcid.org/0009-0004-9151-6607"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Beebe","raw_affiliation_strings":["Texas Tech University,Lubbock,Texas,USA"],"affiliations":[{"raw_affiliation_string":"Texas Tech University,Lubbock,Texas,USA","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002706190","display_name":"Rahulkumar Gayatri","orcid":null},"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":"Rahulkumar Gayatri","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,California,USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,California,USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021316030","display_name":"Kevin Gott","orcid":"https://orcid.org/0000-0003-3244-5525"},"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":"Kevin Gott","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,California,USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,California,USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008625637","display_name":"Adam Lavely","orcid":"https://orcid.org/0000-0002-2994-9004"},"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":"Adam Lavely","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,California,USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,California,USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048512596","display_name":"Muhammad Haseeb","orcid":"https://orcid.org/0000-0003-2208-5984"},"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":"Muhammad Haseeb","raw_affiliation_strings":["NVIDIA Corporation,Santa Clara,California,USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Santa Clara,California,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000643884","display_name":"Brandon Cook","orcid":"https://orcid.org/0000-0002-4203-4079"},"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":"Brandon Cook","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,California,USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,California,USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454473","display_name":"Yong Chen","orcid":"https://orcid.org/0009-0001-6525-6299"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Texas Tech University,Lubbock,Texas,USA"],"affiliations":[{"raw_affiliation_string":"Texas Tech University,Lubbock,Texas,USA","institution_ids":["https://openalex.org/I12315562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5074560418"],"corresponding_institution_ids":["https://openalex.org/I12315562"],"apc_list":null,"apc_paid":null,"fwci":0.3686,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67848656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9890999794006348,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9890999794006348,"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":0.988099992275238,"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":0.9627000093460083,"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":0.7903125882148743},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6826117038726807},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5777661800384521},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5624070167541504},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.5238085985183716},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32392749190330505},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10401690006256104},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10093215107917786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903125882148743},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6826117038726807},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5777661800384521},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5624070167541504},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.5238085985183716},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32392749190330505},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10401690006256104},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10093215107917786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec62836.2024.10938430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","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":13,"referenced_works":["https://openalex.org/W1825216778","https://openalex.org/W2025388037","https://openalex.org/W2057788516","https://openalex.org/W2077783617","https://openalex.org/W2595920247","https://openalex.org/W2944412207","https://openalex.org/W3083442288","https://openalex.org/W3129251660","https://openalex.org/W3201073812","https://openalex.org/W4321636677","https://openalex.org/W4362566335","https://openalex.org/W6685294402","https://openalex.org/W6786127775"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2744553356","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035"],"abstract_inverted_index":{"This":[0,70],"study":[1],"evaluates":[2],"the":[3,15,19,24,29,56],"performance":[4,81],"of":[5,33],"three":[6],"GPU-aware":[7],"MPI":[8,35,77],"implementations-Cray":[9],"MPICH,":[10,11],"and":[12,31,37,44,85,90],"Open":[13],"MPI-on":[14],"Slingshot-11":[16,83],"interconnect":[17],"using":[18],"Perlmutter":[20],"supercomputer.":[21],"We":[22],"use":[23],"OSU":[25],"microbenchmarks":[26],"to":[27,46,87],"evaluate":[28,47],"bandwidth":[30],"latency":[32],"specific":[34],"routines,":[36],"two":[38],"Exascale":[39],"Computing":[40],"Projects":[41],"-":[42],"LAMMPS":[43],"WarpX":[45],"application":[48,63,80],"performance.":[49],"Results":[50],"confirm":[51],"that":[52],"Cray":[53],"MPICH":[54],"outperforms":[55],"others":[57],"over":[58],"Slingshot-11,":[59],"significantly":[60],"influencing":[61],"HPC":[62],"efficiency":[64],"by":[65],"leveraging":[66],"proprietary":[67],"hardware":[68,91],"mechanisms.":[69],"research":[71],"assists":[72],"domain":[73],"scientists":[74],"in":[75],"selecting":[76],"libraries,":[78],"enhancing":[79],"on":[82],"systems":[84],"contributing":[86],"future":[88],"software":[89],"optimization":[92],"studies.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-04T07:04:00.330322","created_date":"2025-10-10T00:00:00"}