{"id":"https://openalex.org/W4281759565","doi":"https://doi.org/10.1145/3514221.3517842","title":"Evaluating Multi-GPU Sorting with Modern Interconnects","display_name":"Evaluating Multi-GPU Sorting with Modern Interconnects","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281759565","doi":"https://doi.org/10.1145/3514221.3517842"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517842","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517842","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","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/A5061080575","display_name":"Tobias Maltenberger","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tobias Maltenberger","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029669802","display_name":"Ivan K. Ilic","orcid":"https://orcid.org/0000-0002-6974-2753"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]},{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ivan Ilic","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023295665","display_name":"Ilin Tolovski","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ilin Tolovski","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002030730","display_name":"Tilmann Rabl","orcid":"https://orcid.org/0009-0009-3335-8045"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tilmann Rabl","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061080575"],"corresponding_institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":3.2301,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.93996403,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1795","last_page":"1809"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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/T11181","display_name":"Advanced Data Storage Technologies","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/T11478","display_name":"Caching and Content Delivery","score":0.9983000159263611,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/pci-express","display_name":"PCI Express","score":0.8933894634246826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.846735954284668},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.7513617277145386},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.715286135673523},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6598451733589172},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.6398171186447144},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6213737726211548},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.45008885860443115},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43409788608551025},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.2872079610824585},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2689485251903534},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11798021197319031},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11464935541152954}],"concepts":[{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.8933894634246826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.846735954284668},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.7513617277145386},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.715286135673523},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6598451733589172},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.6398171186447144},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6213737726211548},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.45008885860443115},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43409788608551025},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2872079610824585},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2689485251903534},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11798021197319031},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11464935541152954},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514221.3517842","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517842","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1902965424","https://openalex.org/W1961751213","https://openalex.org/W1967091776","https://openalex.org/W1974796034","https://openalex.org/W1975755183","https://openalex.org/W1982632559","https://openalex.org/W1993892970","https://openalex.org/W2003515726","https://openalex.org/W2004772832","https://openalex.org/W2005818856","https://openalex.org/W2006552857","https://openalex.org/W2006554829","https://openalex.org/W2039910065","https://openalex.org/W2057671314","https://openalex.org/W2059796743","https://openalex.org/W2059966434","https://openalex.org/W2064190272","https://openalex.org/W2075712468","https://openalex.org/W2080731889","https://openalex.org/W2082695854","https://openalex.org/W2096496252","https://openalex.org/W2102307937","https://openalex.org/W2102639991","https://openalex.org/W2102729946","https://openalex.org/W2112828875","https://openalex.org/W2118558147","https://openalex.org/W2120918807","https://openalex.org/W2162707967","https://openalex.org/W2278783412","https://openalex.org/W2296407087","https://openalex.org/W2406955896","https://openalex.org/W2547543723","https://openalex.org/W2766448074","https://openalex.org/W2808903204","https://openalex.org/W2810532458","https://openalex.org/W2887651661","https://openalex.org/W2903901007","https://openalex.org/W2907714110","https://openalex.org/W2908349016","https://openalex.org/W2926767350","https://openalex.org/W2930869794","https://openalex.org/W2982036057","https://openalex.org/W3016205154","https://openalex.org/W3028661980","https://openalex.org/W3101708369","https://openalex.org/W3129890341","https://openalex.org/W3177047120","https://openalex.org/W6606521517"],"related_works":["https://openalex.org/W2809748609","https://openalex.org/W2095055219","https://openalex.org/W2908348257","https://openalex.org/W3033694952","https://openalex.org/W2994182992","https://openalex.org/W2372558933","https://openalex.org/W2116295091","https://openalex.org/W2362374543","https://openalex.org/W2085265870","https://openalex.org/W2348196682"],"abstract_inverted_index":{"GPUs":[0,79],"have":[1],"become":[2],"a":[3,114,120],"mainstream":[4],"accelerator":[5],"for":[6,147,152],"database":[7],"operations":[8,176],"such":[9],"as":[10],"sorting.":[11],"Most":[12],"GPU":[13,174],"sorting":[14,52,108,125,184],"algorithms":[15],"are":[16],"single-GPU":[17],"approaches.":[18],"They":[19],"neither":[20],"harness":[21],"the":[22,28,180],"full":[23],"computational":[24],"power":[25],"nor":[26],"exploit":[27],"high-bandwidth":[29],"P2P":[30,96,148,159,161],"interconnects":[31,44],"of":[32,143],"modern":[33,132],"multi-GPU":[34,47,51,124],"platforms.":[35,133],"The":[36],"latest":[37],"NVLink":[38,41,85,99],"2.0":[39],"and":[40,69,76,87,119,127,150],"3.0-based":[42,100],"NVSwitch":[43,101],"promise":[45],"unparalleled":[46],"acceleration.":[48],"So":[49],"far,":[50],"has":[53],"only":[54],"been":[55],"evaluated":[56],"on":[57,80,109,130],"systems":[58,81,156],"with":[59,82,98,157],"PCIe":[60,83,103],"3.0.":[61,104],"In":[62],"this":[63],"paper,":[64],"we":[65,112,170],"analyze":[66],"serial,":[67],"parallel,":[68],"bidirectional":[70],"data":[71],"transfer":[72,181],"rates":[73],"to,":[74],"from,":[75],"between":[77],"multiple":[78],"3.0/4.0,":[84],"2.0/3.0,":[86],"NVSwitch.":[88],"We":[89,134],"measure":[90],"up":[91,144,166],"to":[92,145,167],"35x":[93],"higher":[94],"parallel":[95,139],"throughput":[97],"over":[102,137],"To":[105],"study":[106],"GPU-accelerated":[107],"today's":[110],"hardware,":[111],"implement":[113],"P2P-based":[115],"GPU-only":[116],"(P2P":[117],"sort)":[118,123],"heterogeneous":[121],"(HET":[122],"algorithm":[126],"evaluate":[128],"them":[129],"three":[131],"observe":[135],"speedups":[136],"state-of-the-art":[138],"CPU":[140],"radix":[141],"sort":[142,149,162,165],"14x":[146],"9x":[151],"HET":[153,164],"sort.":[154],"On":[155],"fast":[158],"interconnects,":[160],"outperforms":[163],"1.65x.":[168],"Finally,":[169],"show":[171],"that":[172],"overlapping":[173],"copy/compute":[175],"does":[177],"not":[178],"mitigate":[179],"bottleneck":[182],"when":[183],"large":[185],"out-of-core":[186],"data.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
