{"id":"https://openalex.org/W2790216779","doi":"https://doi.org/10.1145/3178442.3178445","title":"An Evaluation of Vectorization and Cache Reuse Tradeoffs on Modern CPUs","display_name":"An Evaluation of Vectorization and Cache Reuse Tradeoffs on Modern CPUs","publication_year":2018,"publication_date":"2018-02-16","ids":{"openalex":"https://openalex.org/W2790216779","doi":"https://doi.org/10.1145/3178442.3178445","mag":"2790216779"},"language":"en","primary_location":{"id":"doi:10.1145/3178442.3178445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178442.3178445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Workshop on Programming Models and Applications for Multicores and Manycores","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/A5052349234","display_name":"Du Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Du Shen","raw_affiliation_strings":["Department of Computer Science, College of William and Mary, Williamsburg, Virgnia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of William and Mary, Williamsburg, Virgnia, USA","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055733971","display_name":"Milind Chabbi","orcid":"https://orcid.org/0000-0003-1021-7644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milind Chabbi","raw_affiliation_strings":["Baidu Research and Scalable Machines Research, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research and Scalable Machines Research, California, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331713","display_name":"Xu Liu","orcid":"https://orcid.org/0000-0002-8984-5485"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":["Department of Computer Science, College of William and Mary, Williamsburg, Virgnia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of William and Mary, Williamsburg, Virgnia, USA","institution_ids":["https://openalex.org/I16285277"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4406,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47407753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9961000084877014,"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/exploit","display_name":"Exploit","score":0.8727211952209473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8719886541366577},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.8206619620323181},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.8011436462402344},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7462787628173828},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5562493801116943},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5530239343643188},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5105019807815552},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.49731209874153137},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.47341352701187134},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42407071590423584},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19129490852355957}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8727211952209473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8719886541366577},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.8206619620323181},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.8011436462402344},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7462787628173828},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5562493801116943},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5530239343643188},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5105019807815552},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.49731209874153137},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.47341352701187134},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42407071590423584},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19129490852355957},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3178442.3178445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178442.3178445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G8010902239","display_name":"CRII: SHF: Optimizing Program Executions on Non-uniform Threaded Architectures","funder_award_id":"1464157","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W38784877","https://openalex.org/W1424657239","https://openalex.org/W1494930385","https://openalex.org/W1963963558","https://openalex.org/W1968797199","https://openalex.org/W2002973181","https://openalex.org/W2005985523","https://openalex.org/W2009725282","https://openalex.org/W2013156670","https://openalex.org/W2018052702","https://openalex.org/W2022740893","https://openalex.org/W2030058342","https://openalex.org/W2044516680","https://openalex.org/W2048968833","https://openalex.org/W2052934867","https://openalex.org/W2055312318","https://openalex.org/W2056304566","https://openalex.org/W2057577013","https://openalex.org/W2064977311","https://openalex.org/W2068326054","https://openalex.org/W2080046548","https://openalex.org/W2080592089","https://openalex.org/W2089672258","https://openalex.org/W2139356353","https://openalex.org/W2142079700","https://openalex.org/W2149590159","https://openalex.org/W2152506070","https://openalex.org/W2158158791","https://openalex.org/W2162726111","https://openalex.org/W2164617852","https://openalex.org/W2170088834","https://openalex.org/W2170653240","https://openalex.org/W2481788784","https://openalex.org/W3006403827","https://openalex.org/W3010071483","https://openalex.org/W3146578712","https://openalex.org/W3149597153","https://openalex.org/W4210645602","https://openalex.org/W4233894383"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W2583128298","https://openalex.org/W2053359564","https://openalex.org/W2161159383","https://openalex.org/W1495260638","https://openalex.org/W1511204342","https://openalex.org/W2369125128","https://openalex.org/W2369223577","https://openalex.org/W2010020348","https://openalex.org/W4238138329"],"abstract_inverted_index":{"Emerging":[0],"high-performance":[1],"processor":[2],"architectures":[3],"show":[4],"two":[5],"key":[6],"trends:":[7],"longer":[8],"vector":[9],"units":[10],"and":[11,24,90,113],"deeper":[12],"memory":[13],"hierarchies.":[14],"It":[15],"is":[16],"not":[17],"always":[18],"possible":[19],"to":[20,54,96,107],"exploit":[21,56],"both":[22,57],"vectorization":[23,33,77,112],"locality.":[25],"Prior":[26],"optimization":[27],"techniques":[28],"have":[29],"focused":[30],"on":[31,118,122,134],"either":[32,55],"for":[34,40],"data":[35],"parallelism":[36],"or":[37,58],"cache":[38],"reuse":[39],"low":[41],"latency":[42],"ignoring":[43],"the":[44,47,60,67,71,109],"interference":[45],"between":[46,111],"two.":[48],"For":[49],"high":[50],"performance,":[51],"software":[52],"needs":[53],"choose":[59],"one":[61],"that":[62,76],"offers":[63],"larger":[64],"gains":[65],"despite":[66],"losses":[68],"incurred":[69],"by":[70,84],"other.":[72],"This":[73],"paper":[74],"demonstrates":[75],"vs.":[78],"locality":[79,117],"tradeoff":[80],"can":[81],"be":[82],"influenced":[83],"code":[85],"shape,":[86],"working":[87],"set":[88],"size,":[89],"architectures.":[91,120,137],"We":[92,101],"first":[93],"devise":[94],"metrics":[95],"precisely":[97],"classify":[98],"these":[99],"tradeoffs.":[100],"then":[102],"design":[103],"representative":[104],"micro":[105],"benchmarks":[106,133],"study":[108],"tradeoffs":[110],"different":[114],"types":[115],"of":[116],"multiple":[119,135],"Based":[121],"our":[123],"learning":[124],"from":[125],"microbenchmark":[126],"studies,":[127],"we":[128],"optimize":[129],"several":[130],"important":[131],"HPC":[132],"CPU":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
