{"id":"https://openalex.org/W2950138172","doi":"https://doi.org/10.1145/3307650.3322257","title":"Duality cache for data parallel acceleration","display_name":"Duality cache for data parallel acceleration","publication_year":2019,"publication_date":"2019-06-14","ids":{"openalex":"https://openalex.org/W2950138172","doi":"https://doi.org/10.1145/3307650.3322257","mag":"2950138172"},"language":"en","primary_location":{"id":"doi:10.1145/3307650.3322257","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3307650.3322257","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3307650.3322257","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International Symposium on Computer Architecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3307650.3322257","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058871698","display_name":"Daichi Fujiki","orcid":"https://orcid.org/0000-0001-7949-0417"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daichi Fujiki","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mahlke","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027544576","display_name":"Reetuparna Das","orcid":"https://orcid.org/0000-0002-5894-8342"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reetuparna Das","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058871698"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":13.084,"has_fulltext":true,"cited_by_count":102,"citation_normalized_percentile":{"value":0.99329199,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"397","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980000257492065,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8576759696006775},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7368228435516357},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.7206892967224121},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7200480699539185},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.7111395001411438},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.6364535093307495},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.6115946769714355},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5957828760147095},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5370800495147705},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.47405359148979187},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.2792273759841919},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2634459435939789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8576759696006775},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7368228435516357},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.7206892967224121},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7200480699539185},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.7111395001411438},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.6364535093307495},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.6115946769714355},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5957828760147095},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5370800495147705},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.47405359148979187},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2792273759841919},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2634459435939789}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3307650.3322257","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3307650.3322257","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3307650.3322257","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3307650.3322257","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3307650.3322257","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3307650.3322257","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2033026803","display_name":"XPS: FULL: Collaborative Research: Enabling Scalable Cloud And Edge-device Integration Using Cross-layer Parallelism","funder_award_id":"1628991","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2236969652","display_name":null,"funder_award_id":"CAREER-1652294, XPS-1628991, SHF-1763918","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G339059864","display_name":null,"funder_award_id":"1652294","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6069466349","display_name":"SHF: Compute Caches: Opportunistic Parallelism in General Purpose Processors at Extreme Scale","funder_award_id":"1763918","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7306266762","display_name":null,"funder_award_id":"CAREER-1652294","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/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950138172.pdf","grobid_xml":"https://content.openalex.org/works/W2950138172.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1975237352","https://openalex.org/W1985956780","https://openalex.org/W1990433043","https://openalex.org/W2013435193","https://openalex.org/W2018658595","https://openalex.org/W2020572638","https://openalex.org/W2021425055","https://openalex.org/W2034861439","https://openalex.org/W2040167141","https://openalex.org/W2043548159","https://openalex.org/W2044829853","https://openalex.org/W2045431893","https://openalex.org/W2075096358","https://openalex.org/W2080592089","https://openalex.org/W2084309410","https://openalex.org/W2086112773","https://openalex.org/W2092324191","https://openalex.org/W2112980698","https://openalex.org/W2115452265","https://openalex.org/W2128046183","https://openalex.org/W2141443190","https://openalex.org/W2159481344","https://openalex.org/W2170257519","https://openalex.org/W2331783522","https://openalex.org/W2464177207","https://openalex.org/W2508602506","https://openalex.org/W2518281301","https://openalex.org/W2613569094","https://openalex.org/W2613989746","https://openalex.org/W2773756426","https://openalex.org/W2794243109","https://openalex.org/W2801000640","https://openalex.org/W2883084140","https://openalex.org/W3000120212","https://openalex.org/W4237024478","https://openalex.org/W4237967454","https://openalex.org/W4239722617","https://openalex.org/W4243519499","https://openalex.org/W4252271806","https://openalex.org/W4254672563"],"related_works":["https://openalex.org/W2133489088","https://openalex.org/W2363769136","https://openalex.org/W2114386333","https://openalex.org/W2126408955","https://openalex.org/W2734782074","https://openalex.org/W2148571123","https://openalex.org/W2396934146","https://openalex.org/W2369103246","https://openalex.org/W2118932116","https://openalex.org/W2115222420"],"abstract_inverted_index":{"Duality":[0,26],"Cache":[1,27],"is":[2],"an":[3],"in-cache":[4,34],"computation":[5],"architecture":[6],"that":[7,49],"enables":[8],"general":[9],"purpose":[10],"data":[11],"parallel":[12],"applications":[13],"to":[14],"run":[15],"on":[16],"caches.":[17],"This":[18],"paper":[19],"presents":[20],"a":[21,42,47],"holistic":[22],"approach":[23],"of":[24,32],"building":[25],"system":[28],"stack":[29],"with":[30],"techniques":[31],"performing":[33],"floating":[35],"point":[36],"arithmetic":[37],"and":[38,54],"transcendental":[39],"functions,":[40],"enabling":[41],"data-parallel":[43],"execution":[44],"model,":[45],"designing":[46],"compiler":[48],"accepts":[50],"existing":[51],"CUDA":[52],"programs,":[53],"providing":[55],"flexibility":[56],"in":[57],"adopting":[58],"for":[59],"various":[60],"workload":[61],"characteristics.":[62]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
