{"id":"https://openalex.org/W2951543943","doi":"https://doi.org/10.1145/3329785.3329922","title":"Performance Analysis and Automatic Tuning of Hash Aggregation on GPUs","display_name":"Performance Analysis and Automatic Tuning of Hash Aggregation on GPUs","publication_year":2019,"publication_date":"2019-06-24","ids":{"openalex":"https://openalex.org/W2951543943","doi":"https://doi.org/10.1145/3329785.3329922","mag":"2951543943"},"language":"en","primary_location":{"id":"doi:10.1145/3329785.3329922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3329785.3329922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Workshop on Data Management on New Hardware","raw_type":"proceedings-article"},"type":"conference-paper","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/A5078503540","display_name":"Viktor Rosenfeld","orcid":"https://orcid.org/0000-0002-6001-4442"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Viktor Rosenfeld","raw_affiliation_strings":["German Research Center for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032404318","display_name":"Sebastian Bre\u00df","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Bre\u00df","raw_affiliation_strings":["German Research Center for Artificial Intelligence and Technische Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence and Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051995830","display_name":"Steffen Zeuch","orcid":"https://orcid.org/0000-0002-4082-7788"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Zeuch","raw_affiliation_strings":["German Research Center for Artificial Intelligence and Technische Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence and Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4577782"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tilmann Rabl","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam amd Technische Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam amd Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806","https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002413906","display_name":"Volker Markl","orcid":"https://orcid.org/0009-0009-0964-026X"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Markl","raw_affiliation_strings":["German Research Center for Artificial Intelligence and Technische Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence and Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9993000030517578,"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/T11478","display_name":"Caching and Content Delivery","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8699320554733276},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.759048581123352},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7410231828689575},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.651498019695282},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.5885143280029297},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.5143362283706665},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4836927056312561},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.45620983839035034},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4490273594856262},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4213883578777313},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32388195395469666},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10717946290969849},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07734966278076172},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07312935590744019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8699320554733276},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.759048581123352},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7410231828689575},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.651498019695282},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.5885143280029297},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5143362283706665},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4836927056312561},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.45620983839035034},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4490273594856262},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4213883578777313},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32388195395469666},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10717946290969849},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07734966278076172},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07312935590744019},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3329785.3329922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3329785.3329922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Workshop on Data Management on New Hardware","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G3305734264","display_name":null,"funder_award_id":"780245","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"},{"id":"https://openalex.org/G4052916464","display_name":null,"funder_award_id":"MA4662-5","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320334604","display_name":"Banting and Best Diabetes Centre, University of Toronto","ror":"https://ror.org/03dbr7087"},{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1984222112","https://openalex.org/W2005294557","https://openalex.org/W2029866183","https://openalex.org/W2067089961","https://openalex.org/W2068418796","https://openalex.org/W2068743743","https://openalex.org/W2102967864","https://openalex.org/W2110975861","https://openalex.org/W2159287299","https://openalex.org/W2255163656","https://openalex.org/W2283004062","https://openalex.org/W2342922783","https://openalex.org/W2407123212","https://openalex.org/W2424351436","https://openalex.org/W2547123334","https://openalex.org/W2548100623","https://openalex.org/W2752640170","https://openalex.org/W2798422034","https://openalex.org/W2911324315","https://openalex.org/W3198160809"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Hash":[0],"aggregation":[1,25,47],"is":[2,74],"an":[3,105],"important":[4],"data":[5],"processing":[6],"primitive":[7],"which":[8],"can":[9],"be":[10],"significantly":[11],"accelerated":[12],"by":[13],"modern":[14],"graphics":[15],"processors":[16],"(GPUs).":[17],"Previous":[18],"work":[19],"derived":[20],"heuristics":[21],"for":[22,87,129],"GPU-accelerated":[23,45],"hash":[24,46],"from":[26],"the":[27,38,68,126,134,151,159,174],"study":[28],"of":[29,40,67,125,133,155],"a":[30,88,119,130],"particular":[31],"GPU.":[32],"In":[33,137,158],"this":[34,100,138],"paper,":[35],"we":[36,61,103],"examine":[37],"influence":[39],"different":[41,58],"execution":[42,77,84,109,142,165],"parameters":[43,78,85,110,143,166],"on":[44,48,56,96,118],"four":[49],"NVIDIA":[50],"and":[51],"two":[52],"AMD":[53],"GPUs":[54],"based":[55],"six":[57],"microarchitectures.":[59],"While":[60],"are":[62,79,91,145,168],"able":[63],"to":[64,93,107],"replicate":[65],"some":[66],"previous":[69],"results,":[70],"our":[71,115,156,162],"main":[72],"finding":[73],"that":[75,144,167],"optimal":[76],"highly":[80],"GPU-dependent.":[81],"Most":[82],"importantly,":[83],"optimized":[86],"specific":[89],"GPU":[90],"up":[92],"21x":[94],"slower":[95,149,172],"other":[97],"GPUs.":[98],"Given":[99],"hardware":[101],"dependency,":[102],"present":[104],"algorithm":[106,116,163],"optimize":[108],"at":[111,146,169],"runtime.":[112],"On":[113],"average,":[114],"converges":[117],"result":[120],"in":[121,153],"less":[122],"than":[123,150,173],"1%":[124,148],"time":[127],"required":[128],"full":[131],"evaluation":[132],"search":[135],"space.":[136],"time,":[139],"it":[140],"finds":[141,164],"most":[147,170],"optimum":[152],"90%":[154],"experiments.":[157],"worst":[160],"case,":[161],"1.29x":[171],"optimum.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
