{"id":"https://openalex.org/W4388581217","doi":"https://doi.org/10.1145/3624062.3624182","title":"Evaluating the Performance of One-sided Communication on CPUs and GPUs","display_name":"Evaluating the Performance of One-sided Communication on CPUs and GPUs","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581217","doi":"https://doi.org/10.1145/3624062.3624182"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624182","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624182","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011195132","display_name":"Nan Ding","orcid":"https://orcid.org/0000-0001-9624-9449"},"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":"Nan Ding","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0001-9624-9449","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082182788","display_name":"Muhammad Haseeb","orcid":"https://orcid.org/0000-0002-0697-6894"},"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":"Muhammad Haseeb","raw_affiliation_strings":["Lawrence Berkeley National Laboratory (LBNL), United States of America"],"raw_orcid":"https://orcid.org/0000-0002-0697-6894","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory (LBNL), United States of America","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077281296","display_name":"Taylor Groves","orcid":"https://orcid.org/0000-0002-7020-8881"},"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":"Taylor Groves","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-7020-8881","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"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":"Samuel Williams","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-8327-5717","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":1.0439,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81719834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1059","last_page":"1069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7298320531845093},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6701541543006897},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3722671866416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7298320531845093},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6701541543006897},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3722671866416931}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3624062.3624182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624182","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624182","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"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt07h894jk","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/07h894jk","pdf_url":"https://escholarship.org/content/qt07h894jk/qt07h894jk.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:ark:/13030/qt07h894jk","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3624062.3624182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624182","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624182","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":[{"id":"https://openalex.org/G1286236842","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1677143136","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G1799333409","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G3083819904","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3944918260","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4370606643","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G4501827968","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4565140552","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5076365615","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G6348972864","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7368046788","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7651947074","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581217.pdf","grobid_xml":"https://content.openalex.org/works/W4388581217.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1588544414","https://openalex.org/W1975934607","https://openalex.org/W1980759071","https://openalex.org/W2002555321","https://openalex.org/W2012313745","https://openalex.org/W2042120213","https://openalex.org/W2129418947","https://openalex.org/W2795994638","https://openalex.org/W2926767350","https://openalex.org/W2998812396","https://openalex.org/W3001467520","https://openalex.org/W3046421657","https://openalex.org/W3101708369","https://openalex.org/W3122949375","https://openalex.org/W4200537641","https://openalex.org/W4245836145"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Effective":[0],"programming":[1,150],"models":[2],"offer":[3],"programmers":[4],"the":[5,9,12,17,43,58,66,130,147,180,198],"ability":[6],"to":[7,128],"harness":[8],"capabilities":[10],"of":[11,60,68,71,109,114,132,201],"underlying":[13],"platform.":[14],"For":[15],"decades,":[16],"two-sided":[18,181],"Message":[19,95],"Passing":[20],"Interface":[21],"(MPI)":[22],"has":[23],"become":[24],"a":[25,49,83,94,107],"de":[26],"facto":[27],"standard":[28],"for":[29,52],"communication":[30,47,62,73,134],"among":[31],"processes":[32],"running":[33],"on":[34,63,78,135],"distributed":[35],"memory":[36],"systems.":[37],"As":[38],"high-performance":[39],"GPU":[40],"computing":[41],"becomes":[42,48,82],"trend,":[44],"GPU-initiated":[45],"one-sided":[46,61,72,133,183,202],"viable":[50],"solution":[51],"multi-GPU":[53],"scaling.":[54],"It":[55],"also":[56,190],"highlights":[57],"use":[59,125],"CPUs.":[64],"However,":[65],"lack":[67],"deep":[69],"understanding":[70,179],"performance":[74,81,104,200],"and":[75,121,137,165,171,182,188],"its":[76,110],"impact":[77],"an":[79,100],"application\u2019s":[80,101],"hurdle.":[84],"In":[85],"this":[86,90],"paper,":[87],"we":[88],"overcome":[89],"hurdle":[91],"by":[92],"proposing":[93],"Roofline":[96],"model,":[97,151],"which":[98],"characterizes":[99],"sustained":[102],"messaging":[103],"(GB/s)":[105],"as":[106],"function":[108],"message":[111],"size,":[112],"number":[113],"messages":[115],"per":[116],"synchronization,":[117],"peak":[118],"network":[119,122],"bandwidth,":[120],"latency.":[123],"We":[124],"three":[126],"benchmarks":[127,140],"demonstrate":[129],"potentials":[131],"CPUs":[136],"GPUs.":[138],"These":[139],"include":[141],"Stencils":[142],"representing":[143,155],"applications":[144],"that":[145,160],"follow":[146],"bulk":[148],"synchronization":[149],"Sparse":[152],"Triangular":[153],"Solve":[154],"directed":[156],"acyclic":[157],"graph":[158],"computations":[159],"perform":[161],"asynchronous":[162],"point-to-point":[163],"communications,":[164],"Distributed":[166],"HashTable":[167],"performing":[168],"atomic":[169],"compare":[170],"swaps.":[172],"Our":[173],"evaluation":[174],"provides":[175],"insights":[176],"into":[177],"practically":[178],"communications":[184,203],"in":[185],"MPI":[186],"applications,":[187],"can":[189],"guide":[191],"hardware":[192],"vendors":[193],"with":[194],"design":[195],"principles":[196],"lest":[197],"potential":[199],"being":[204],"under-utilized.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}
