{"id":"https://openalex.org/W3193720746","doi":"https://doi.org/10.1145/3468267.3470618","title":"Memory reduction using a ring abstraction over GPU RDMA for distributed quantum Monte Carlo solver","display_name":"Memory reduction using a ring abstraction over GPU RDMA for distributed quantum Monte Carlo solver","publication_year":2021,"publication_date":"2021-07-05","ids":{"openalex":"https://openalex.org/W3193720746","doi":"https://doi.org/10.1145/3468267.3470618","mag":"3193720746"},"language":"en","primary_location":{"id":"doi:10.1145/3468267.3470618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468267.3470618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.lsu.edu/eecs_pubs/2476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030037263","display_name":"Weile Wei","orcid":"https://orcid.org/0000-0002-3065-4959"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weile Wei","raw_affiliation_strings":["Louisiana State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067338164","display_name":"E. D\u2019Azevedo","orcid":"https://orcid.org/0000-0002-6945-3206"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduardo D'Azevedo","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104385228","display_name":"Kevin Huck","orcid":"https://orcid.org/0000-0001-7064-8417"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Huck","raw_affiliation_strings":["University of Oregon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oregon","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038874000","display_name":"Arghya Chatterjee","orcid":"https://orcid.org/0000-0002-7259-2944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arghya Chatterjee","raw_affiliation_strings":["NERSC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071822072","display_name":"\u00d3scar Hern\u00e1ndez","orcid":"https://orcid.org/0000-0002-5380-6951"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oscar Hernandez","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051320432","display_name":"Hartmut Kaiser","orcid":"https://orcid.org/0000-0002-8712-2806"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hartmut Kaiser","raw_affiliation_strings":["Louisiana State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3224,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58876877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10037","display_name":"Physics of Superconductivity and Magnetism","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10037","display_name":"Physics of Superconductivity and Magnetism","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965000152587891,"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":0.9939000010490417,"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":0.7979720830917358},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.6836022138595581},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6157568693161011},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.4454543888568878},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4184441566467285},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.4168230891227722},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3658822774887085},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3554307222366333},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15070942044258118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979720830917358},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.6836022138595581},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6157568693161011},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.4454543888568878},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4184441566467285},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4168230891227722},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3658822774887085},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3554307222366333},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15070942044258118},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3468267.3470618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468267.3470618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-3478","is_oa":true,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/2476","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-3478","is_oa":true,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/2476","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2036941747","https://openalex.org/W2048744802","https://openalex.org/W2078746091","https://openalex.org/W2985909487","https://openalex.org/W3082389863","https://openalex.org/W3098040606","https://openalex.org/W3132974082","https://openalex.org/W4288356921"],"related_works":["https://openalex.org/W1978254186","https://openalex.org/W4245217724","https://openalex.org/W4390917331","https://openalex.org/W4253931064","https://openalex.org/W1984788566","https://openalex.org/W3166154920","https://openalex.org/W2154082760","https://openalex.org/W1964981582","https://openalex.org/W4282599985","https://openalex.org/W1602284866"],"abstract_inverted_index":{"Scientific":[0],"applications":[1],"that":[2,152,189],"run":[3],"on":[4,77,147],"leadership":[5],"computing":[6],"facilities":[7],"often":[8],"face":[9],"the":[10,32,92,122,136,140,148,153,157,171,177,182,190,204,210],"challenge":[11],"of":[12,39,75,170,179,206],"being":[13],"unable":[14],"to":[15,24,103,168],"fit":[16],"leading":[17],"science":[18],"cases":[19],"onto":[20],"accelerator":[21],"devices":[22],"due":[23],"memory":[25,82,145],"constraints":[26],"(memory-bound":[27],"applications).":[28],"In":[29],"this":[30,51,132],"work,":[31],"authors":[33],"studied":[34],"one":[35],"such":[36],"US":[37],"Department":[38],"Energy":[40],"mission-critical":[41],"condensed":[42],"matter":[43],"physics":[44],"application,":[45],"Dynamical":[46],"Cluster":[47],"Approximation":[48],"(DCA++),":[49],"and":[50,79,100,108,115,131,203],"paper":[52,133],"discusses":[53,135],"how":[54],"device":[55],"memory-bound":[56],"challenges":[57],"were":[58,117],"successfully":[59],"reduced":[60,167],"by":[61,120],"proposing":[62],"an":[63],"effective":[64],"\"all-to-all\"":[65],"communication":[66,69,106,116,186],"method---a":[67],"ring":[68,93,141,149,183],"algorithm.":[70],"This":[71],"implementation":[72],"takes":[73],"advantage":[74],"acceleration":[76],"GPUs":[78,180],"remote":[80],"direct":[81],"access":[83],"(RDMA)":[84],"for":[85,126,139,156],"fast":[86],"data":[87,161],"exchange":[88],"between":[89],"GPUs.":[90],"Additionally,":[91],"algorithm":[94,142,150],"was":[95],"optimized":[96],"with":[97],"sub-ring":[98,200],"communicators":[99],"multi-threaded":[101],"support":[102],"further":[104,134],"reduce":[105],"overhead":[107],"expose":[109],"more":[110],"concurrency,":[111],"respectively.":[112],"The":[113,144,185],"computation":[114],"also":[118],"analyzed":[119],"using":[121],"Autonomic":[123],"Performance":[124],"Environment":[125],"Exascale":[127],"(APEX)":[128],"profiling":[129],"tool,":[130],"performance":[137],"trade-off":[138],"implementation.":[143],"analysis":[146,187],"shows":[151],"allocation":[154],"size":[155,201],"authors'":[158],"most":[159],"memory-intensive":[160],"structure":[162],"per":[163],"GPU":[164],"is":[165,176],"now":[166],"1/p":[169],"original":[172],"size,":[173],"where":[174],"p":[175],"number":[178],"in":[181],"communicator.":[184],"suggests":[188],"distributed":[191],"Quantum":[192],"Monte":[193],"Carlo":[194],"execution":[195],"time":[196],"grows":[197],"linearly":[198],"as":[199],"increases,":[202],"cost":[205],"messages":[207],"passing":[208],"through":[209],"network":[211],"interface":[212],"connector":[213],"could":[214],"be":[215],"a":[216],"limiting":[217],"factor.":[218]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
