{"id":"https://openalex.org/W4389628071","doi":"https://doi.org/10.1145/3626751","title":"Rethinking the Encoding of Integers for Scans on Skewed Data","display_name":"Rethinking the Encoding of Integers for Scans on Skewed Data","publication_year":2023,"publication_date":"2023-12-08","ids":{"openalex":"https://openalex.org/W4389628071","doi":"https://doi.org/10.1145/3626751"},"language":"en","primary_location":{"id":"doi:10.1145/3626751","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626751","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626751","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3626751","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021820528","display_name":"Martin Prammer","orcid":"https://orcid.org/0009-0000-4348-236X"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Martin Prammer","raw_affiliation_strings":["University of Wisconsin - Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin - Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021820528"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.3994,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64139098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"1","issue":"4","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.980400025844574,"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/pruning","display_name":"Pruning","score":0.7835745811462402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767426609992981},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6676997542381287},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5145363211631775},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47939634323120117},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4520948529243469},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4432935118675232},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.4219372272491455},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.321420282125473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22292491793632507},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16147619485855103},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14314138889312744}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7835745811462402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767426609992981},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6676997542381287},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5145363211631775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47939634323120117},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4520948529243469},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4432935118675232},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.4219372272491455},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.321420282125473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22292491793632507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16147619485855103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14314138889312744},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626751","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626751","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626751","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3626751","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626751","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626751","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G171229425","display_name":"Collaborative Research: SHF: Medium: A hardware-software co-design approach for high-performance in-memory analytic data processing","funder_award_id":"2312739","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2053563072","display_name":null,"funder_award_id":"CRISP","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G7406030291","display_name":null,"funder_award_id":"CRISP","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7538461470","display_name":"Elements: Software: Towards Efficient Embedded Data Processing","funder_award_id":"1835446","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389628071.pdf","grobid_xml":"https://content.openalex.org/works/W4389628071.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1578512165","https://openalex.org/W1967983783","https://openalex.org/W1987238352","https://openalex.org/W1991223838","https://openalex.org/W2014842542","https://openalex.org/W2055774867","https://openalex.org/W2070593325","https://openalex.org/W2091459966","https://openalex.org/W2096496252","https://openalex.org/W2100542992","https://openalex.org/W2103670492","https://openalex.org/W2111967617","https://openalex.org/W2113831242","https://openalex.org/W2115613939","https://openalex.org/W2117489143","https://openalex.org/W2123686039","https://openalex.org/W2128777897","https://openalex.org/W2135828943","https://openalex.org/W2138981210","https://openalex.org/W2143125604","https://openalex.org/W2146461854","https://openalex.org/W2147076738","https://openalex.org/W2163422235","https://openalex.org/W2396727930","https://openalex.org/W2752061190","https://openalex.org/W2766489088","https://openalex.org/W2794610196","https://openalex.org/W2951621897","https://openalex.org/W3016903199","https://openalex.org/W3175356203","https://openalex.org/W3191503410","https://openalex.org/W4233996382","https://openalex.org/W4296079271","https://openalex.org/W4297812065","https://openalex.org/W6677064796"],"related_works":["https://openalex.org/W2534771569","https://openalex.org/W2037547261","https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W4311812695","https://openalex.org/W2117788426","https://openalex.org/W4242015792","https://openalex.org/W3011583392","https://openalex.org/W2128223750"],"abstract_inverted_index":{"Bit-parallel":[0],"scanning":[1],"techniques":[2,20,76,103,135],"are":[3],"characterized":[4],"by":[5,97,232],"their":[6],"ability":[7],"to":[8,31,72,122,146,180],"accelerate":[9],"compute":[10,34],"through":[11],"the":[12,23,50,57,98,129,156,166,181,193,198,205,220],"process":[13],"known":[14],"as":[15],"early":[16,53,116],"pruning.":[17],"Early":[18],"pruning":[19,54,67,117],"iterate":[21],"over":[22],"bits":[24,61,178],"of":[25,46,52,60,131,168,173,207],"each":[26,38,69],"value,":[27],"searching":[28],"for":[29,66],"opportunities":[30],"safely":[32],"prune":[33],"early,":[35],"before":[36],"processing":[37,82],"data":[39],"value":[40],"in":[41,128,158,229],"its":[42],"entirety.":[43],"However,":[44],"because":[45],"this":[47,73,152,186],"iterative":[48],"evaluation,":[49],"effectiveness":[51],"depends":[55],"on":[56],"relative":[58],"position":[59],"that":[62,101,114,175],"can":[63],"be":[64],"used":[65],"within":[68],"value.":[70,126],"Due":[71],"behavior,":[74],"bit-parallel":[75,102,134,159,223],"have":[77],"faced":[78],"significant":[79,183],"challenges":[80],"when":[81,86,144],"skewed":[83,132],"data,":[84,133],"especially":[85],"values":[87,157],"contain":[88],"many":[89,230],"leading":[90],"zeroes.":[91],"This":[92],"problem":[93],"is":[94],"further":[95],"amplified":[96],"inherent":[99],"trade-off":[100],"make":[104],"between":[105],"columnar":[106,148],"scan":[107,142,225],"and":[108,197,226,234],"fetch":[109,123,137,227],"performance:":[110],"a":[111,124,171],"storage":[112],"layer":[113],"supports":[115],"requires":[118],"multiple":[119,211],"memory":[120],"accesses":[121],"single":[125],"Thus,":[127],"case":[130],"increase":[136],"latency":[138],"without":[139],"significantly":[140],"improving":[141],"performance":[143,228],"compared":[145],"baseline":[147],"implementations.":[149],"To":[150],"remedy":[151],"shortcoming,":[153],"we":[154,188],"transform":[155],"columns":[160],"using":[161,210],"novel":[162],"encodings.":[163],"We":[164,203],"propose":[165,189],"concept":[167],"forward":[169,217],"encodings:":[170,192],"family":[172],"encodings":[174,209,218],"shift":[176],"pruning-relevant":[177],"closer":[179],"most":[182],"bit.":[184],"Using":[185],"concept,":[187],"two":[190],"particular":[191],"Data":[194,200],"Forward":[195,201],"Encoding":[196],"Extended":[199],"Encoding.":[202],"demonstrate":[204],"impact":[206],"these":[208,215],"real-world":[212],"datasets.":[213],"Across":[214],"datasets,":[216],"improve":[219],"current":[221],"state-of-the-art":[222],"technique's":[224],"cases":[231],"1.4x":[233],"1.3x,":[235],"respectively.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}