{"id":"https://openalex.org/W2158626113","doi":"https://doi.org/10.1109/ipdps.2009.5161054","title":"A scalable auto-tuning framework for compiler optimization","display_name":"A scalable auto-tuning framework for compiler optimization","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2158626113","doi":"https://doi.org/10.1109/ipdps.2009.5161054","mag":"2158626113"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2009.5161054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5161054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","raw_type":"proceedings-article"},"type":"article","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/A5000364746","display_name":"Ananta Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananta Tiwari","raw_affiliation_strings":["Department of Computer Science, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103956520","display_name":"Chun Chen","orcid":"https://orcid.org/0009-0005-8416-9587"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun Chen","raw_affiliation_strings":["School of Computing, University of Utah, Salt Lake, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Utah, Salt Lake, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057351225","display_name":"Jacqueline Chame","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacqueline Chame","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina del Ray, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina del Ray, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["Department of Computer Science, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113657683","display_name":"Jeffrey K. Hollingsworth","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey K. Hollingsworth","raw_affiliation_strings":["Department of Computer Science, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.1575,"has_fulltext":false,"cited_by_count":218,"citation_normalized_percentile":{"value":0.99366011,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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":0.995199978351593,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9923999905586243,"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/compiler","display_name":"Compiler","score":0.9174343347549438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8964054584503174},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7652416229248047},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6461859345436096},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.5826278924942017},{"id":"https://openalex.org/keywords/interprocedural-optimization","display_name":"Interprocedural optimization","score":0.5399695634841919},{"id":"https://openalex.org/keywords/compiler-correctness","display_name":"Compiler correctness","score":0.5220263600349426},{"id":"https://openalex.org/keywords/loop-optimization","display_name":"Loop optimization","score":0.49528470635414124},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.48578765988349915},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4849669933319092},{"id":"https://openalex.org/keywords/just-in-time-compilation","display_name":"Just-in-time compilation","score":0.4622288644313812},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45163118839263916},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.4491337835788727},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4415474236011505},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.426663339138031},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41673731803894043},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19809463620185852},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.19727569818496704}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.9174343347549438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8964054584503174},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7652416229248047},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6461859345436096},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.5826278924942017},{"id":"https://openalex.org/C111564260","wikidata":"https://www.wikidata.org/wiki/Q4288856","display_name":"Interprocedural optimization","level":5,"score":0.5399695634841919},{"id":"https://openalex.org/C68366613","wikidata":"https://www.wikidata.org/wiki/Q5156378","display_name":"Compiler correctness","level":3,"score":0.5220263600349426},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.49528470635414124},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.48578765988349915},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4849669933319092},{"id":"https://openalex.org/C76782552","wikidata":"https://www.wikidata.org/wiki/Q110546","display_name":"Just-in-time compilation","level":3,"score":0.4622288644313812},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45163118839263916},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4491337835788727},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4415474236011505},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.426663339138031},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41673731803894043},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19809463620185852},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.19727569818496704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2009.5161054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5161054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.2200","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.2200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umd.edu/~hollings/papers/ipdps09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1491410022","https://openalex.org/W1606633049","https://openalex.org/W1972209410","https://openalex.org/W2007451249","https://openalex.org/W2031775479","https://openalex.org/W2034761517","https://openalex.org/W2071110673","https://openalex.org/W2072277531","https://openalex.org/W2076346710","https://openalex.org/W2099059741","https://openalex.org/W2099625934","https://openalex.org/W2112502633","https://openalex.org/W2119691711","https://openalex.org/W2126464777","https://openalex.org/W2135653967","https://openalex.org/W2152503947","https://openalex.org/W2162404488","https://openalex.org/W2164197394","https://openalex.org/W2168519934","https://openalex.org/W2314944927","https://openalex.org/W2427881153","https://openalex.org/W2626636781","https://openalex.org/W3136479147","https://openalex.org/W4243796884","https://openalex.org/W6683955988","https://openalex.org/W6739759859"],"related_works":["https://openalex.org/W2083681681","https://openalex.org/W2479014312","https://openalex.org/W1597127505","https://openalex.org/W2013570895","https://openalex.org/W2049890071","https://openalex.org/W2577630842","https://openalex.org/W2036668966","https://openalex.org/W1583465708","https://openalex.org/W1575999420","https://openalex.org/W2158626113"],"abstract_inverted_index":{"We":[0,11],"describe":[1],"a":[2,28,100],"scalable":[3],"and":[4,36,94],"general-purpose":[5],"framework":[6,23],"for":[7,63,68],"auto-tuning":[8],"compiler-generated":[9,51],"code.":[10],"combine":[12],"Active":[13],"Harmony's":[14],"parallel":[15,27],"search":[16,85],"backend":[17],"with":[18,41],"the":[19,39,42,55,60,64,78],"CHiLL":[20],"compiler":[21,81,92],"transformation":[22],"to":[24,54,73,96],"generate":[25],"in":[26,98],"set":[29],"of":[30,33,50,59,91,103],"alternative":[31],"implementations":[32],"computation":[34],"kernels":[35,70],"automatically":[37],"select":[38],"one":[40],"best-performing":[43],"implementation.":[44],"The":[45],"resulting":[46],"system":[47],"achieves":[48],"performance":[49],"code":[52],"comparable":[53],"fully":[56],"automated":[57],"version":[58],"ATLAS":[61],"library":[62],"tested":[65],"kernels.":[66],"Performance":[67],"various":[69],"is":[71],"1.4":[72],"3.6":[74],"times":[75],"faster":[76],"than":[77],"native":[79],"Intel":[80],"without":[82],"search.":[83],"Our":[84],"algorithm":[86],"simultaneously":[87],"evaluates":[88],"different":[89],"combinations":[90],"optimizations":[93],"converges":[95],"solutions":[97],"only":[99],"few":[101],"tens":[102],"search-steps.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":25}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}