{"id":"https://openalex.org/W4412150126","doi":"https://doi.org/10.1145/3736227.3736238","title":"Insert-Optimized Implementation of Streaming Data Sketches","display_name":"Insert-Optimized Implementation of Streaming Data Sketches","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4412150126","doi":"https://doi.org/10.1145/3736227.3736238"},"language":"en","primary_location":{"id":"doi:10.1145/3736227.3736238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736227.3736238","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736227.3736238","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 21st International Workshop on Data Management on New Hardware","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/10.1145/3736227.3736238","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063387634","display_name":"Pascal Pfeil","orcid":"https://orcid.org/0009-0001-6719-604X"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pascal Pfeil","raw_affiliation_strings":["Amazon Web Services, Munich, Germany"],"raw_orcid":"https://orcid.org/0009-0001-6719-604X","affiliations":[{"raw_affiliation_string":"Amazon Web Services, Munich, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039503096","display_name":"Dominik Horn","orcid":"https://orcid.org/0009-0009-4489-1638"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Horn","raw_affiliation_strings":["Amazon Web Services, Munich, Germany"],"raw_orcid":"https://orcid.org/0009-0009-4489-1638","affiliations":[{"raw_affiliation_string":"Amazon Web Services, Munich, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077806101","display_name":"Orestis Polychroniou","orcid":"https://orcid.org/0000-0002-3164-0137"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Orestis Polychroniou","raw_affiliation_strings":["Amazon Web Services, East Palo Alto, USA"],"raw_orcid":"https://orcid.org/0000-0002-3164-0137","affiliations":[{"raw_affiliation_string":"Amazon Web Services, East Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118883713","display_name":"George Erickson","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Erickson","raw_affiliation_strings":["Amazon Web Services, Boston, USA"],"raw_orcid":"https://orcid.org/0009-0004-7736-0669","affiliations":[{"raw_affiliation_string":"Amazon Web Services, Boston, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118883714","display_name":"Zhe Heng Eng","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Heng Eng","raw_affiliation_strings":["Amazon Web Services, East Palo Alto, USA"],"raw_orcid":"https://orcid.org/0009-0001-5963-6949","affiliations":[{"raw_affiliation_string":"Amazon Web Services, East Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013935501","display_name":"Mengchu Cai","orcid":"https://orcid.org/0000-0001-5224-3723"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengchu Cai","raw_affiliation_strings":["Amazon Web Services, East Palo Alto, USA"],"raw_orcid":"https://orcid.org/0009-0000-8938-6605","affiliations":[{"raw_affiliation_string":"Amazon Web Services, East Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["Amazon Web Services, Boston, USA"],"raw_orcid":"https://orcid.org/0009-0003-2414-2759","affiliations":[{"raw_affiliation_string":"Amazon Web Services, Boston, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16036404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","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/T10317","display_name":"Advanced Database Systems and Queries","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/T11106","display_name":"Data Management and Algorithms","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9965999722480774,"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":0.7580863833427429},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.6830250024795532},{"id":"https://openalex.org/keywords/insert","display_name":"Insert (composites)","score":0.4149150550365448},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.140375018119812},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07989233732223511}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580863833427429},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.6830250024795532},{"id":"https://openalex.org/C2780098074","wikidata":"https://www.wikidata.org/wiki/Q6037362","display_name":"Insert (composites)","level":2,"score":0.4149150550365448},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.140375018119812},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07989233732223511},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3736227.3736238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736227.3736238","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736227.3736238","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 21st International Workshop on Data Management on New Hardware","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3736227.3736238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736227.3736238","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736227.3736238","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 21st International Workshop on Data Management on New Hardware","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412150126.pdf","grobid_xml":"https://content.openalex.org/works/W4412150126.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1970779762","https://openalex.org/W2006355640","https://openalex.org/W2080234606","https://openalex.org/W2123964197","https://openalex.org/W2144982963","https://openalex.org/W2439904216","https://openalex.org/W2605823630","https://openalex.org/W2753629899","https://openalex.org/W2798945787","https://openalex.org/W2834288129","https://openalex.org/W2890611883","https://openalex.org/W2963274201","https://openalex.org/W2963898466","https://openalex.org/W3004286518","https://openalex.org/W3016354376","https://openalex.org/W3146390850","https://openalex.org/W4214495955","https://openalex.org/W4283323602","https://openalex.org/W4388620448","https://openalex.org/W4389315109","https://openalex.org/W4393180322"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2167951155","https://openalex.org/W4244087614","https://openalex.org/W2355051413","https://openalex.org/W2024714645","https://openalex.org/W2372066122","https://openalex.org/W4255333527","https://openalex.org/W2384129116"],"abstract_inverted_index":{"We":[0],"present":[1],"insert-optimized":[2],"implementations":[3,107,150],"of":[4,37,61,155],"three":[5],"fundamental":[6],"data":[7],"sketching":[8],"algorithms:":[9],"Count":[10,137],"Sketch":[11],"(CS),":[12],"SpaceSaving":[13],"(SS),":[14],"and":[15,27,43,55,66,71,98,114,133,143,145],"Karnin-Lang-Liberty":[16],"(KLL).While":[17],"these":[18,126],"sketches":[19],"are":[20],"widely":[21],"used":[22,108],"for":[23,68,93,96,100,136,141,148,170],"approximate":[24],"query":[25],"processing":[26],"stream":[28],"analytics,":[29],"their":[30,38],"practical":[31,163],"insert":[32,164],"performance":[33],"often":[34],"falls":[35],"short":[36],"full":[39],"potential.Through":[40],"careful":[41],"engineering":[42],"novel":[44],"implementation":[45],"strategies,":[46],"we":[47,86],"achieve":[48,87],"substantial":[49],"throughput":[50],"improvements":[51,147],"over":[52],"both":[53],"na\u00efve":[54,84],"existing":[56],"implementations.Our":[57],"approach":[58],"demonstrates":[59],"speedups":[60],"up":[62],"to":[63,76],"12.30x,":[64],"2.00x,":[65],"1.52x":[67],"CS,":[69,94],"SS,":[70,97],"KLL":[72],"respectively":[73],"when":[74],"compared":[75],"the":[77,122,152,156],"industry-standard":[78],"Apache":[79],"DataSketches":[80],"library.When":[81],"measured":[82],"against":[83,104],"implementations,":[85],"even":[88],"more":[89],"dramatic":[90],"improvements:":[91],"8.63x":[92],"7.03x":[95],"446.00x":[99],"KLL.We":[101],"also":[102],"measure":[103],"available":[105],"open-source":[106],"as":[109],"baselines":[110],"in":[111],"other":[112],"works":[113],"outperform":[115],"them":[116,167],"by":[117],"a":[118],"large":[119],"margin.We":[120],"detail":[121],"technical":[123],"optimizations":[124],"enabling":[125],"improvements,":[127],"including":[128],"fast":[129],"hash":[130,134],"range":[131],"reduction":[132],"sharing":[135],"Sketch,":[138],"SIMD":[139],"vectorization":[140],"SpaceSaving,":[142],"preallocation":[144],"branching":[146],"Karnin-Lang-Liberty.Our":[149],"maintain":[151],"theoretical":[153],"guarantees":[154],"original":[157],"algorithms":[158],"while":[159],"providing":[160],"substantially":[161],"better":[162],"performance,":[165],"making":[166],"particularly":[168],"valuable":[169],"high-throughput":[171],"streaming":[172],"applications":[173],"where":[174],"update":[175],"speed":[176],"is":[177],"critical.":[178]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}