{"id":"https://openalex.org/W2064508949","doi":"https://doi.org/10.1145/1509864.1509866","title":"A SIMD optimization framework for retargetable compilers","display_name":"A SIMD optimization framework for retargetable compilers","publication_year":2009,"publication_date":"2009-03-30","ids":{"openalex":"https://openalex.org/W2064508949","doi":"https://doi.org/10.1145/1509864.1509866","mag":"2064508949"},"language":"en","primary_location":{"id":"doi:10.1145/1509864.1509866","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1509864.1509866","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1509864.1509866","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/1509864.1509866","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034406879","display_name":"Manuel Hohenauer","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Manuel Hohenauer","raw_affiliation_strings":["RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030277592","display_name":"Felix Engel","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Engel","raw_affiliation_strings":["RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023470562","display_name":"Rainer Leupers","orcid":"https://orcid.org/0000-0002-6735-3033"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Leupers","raw_affiliation_strings":["RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050903837","display_name":"Gerd Ascheid","orcid":"https://orcid.org/0000-0003-4068-3558"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerd Ascheid","raw_affiliation_strings":["RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020992230","display_name":"H. Meyr","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Heinrich Meyr","raw_affiliation_strings":["RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034406879"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":3.7521,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93506862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"6","issue":"1","first_page":"1","last_page":"27"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.998199999332428,"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":0.9944000244140625,"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/simd","display_name":"SIMD","score":0.9229596853256226},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8994721174240112},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8821797966957092},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7080193758010864},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6259279251098633},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45950740575790405},{"id":"https://openalex.org/keywords/very-long-instruction-word","display_name":"Very long instruction word","score":0.4472615420818329},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.4286731481552124},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.42838963866233826},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40411216020584106},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3101330101490021},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.20763519406318665},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.1471107006072998},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08622699975967407}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9229596853256226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8994721174240112},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8821797966957092},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7080193758010864},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6259279251098633},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45950740575790405},{"id":"https://openalex.org/C170595534","wikidata":"https://www.wikidata.org/wiki/Q249743","display_name":"Very long instruction word","level":2,"score":0.4472615420818329},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4286731481552124},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.42838963866233826},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40411216020584106},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3101330101490021},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.20763519406318665},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.1471107006072998},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08622699975967407}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1509864.1509866","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1509864.1509866","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1509864.1509866","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:publications.rwth-aachen.de:133346","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/133346","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM transactions on architecture and code optimization 6(1), 1-27 (2009). doi:10.1145/1509864.1509866","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/1509864.1509866","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1509864.1509866","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1509864.1509866","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W22487599","https://openalex.org/W127897580","https://openalex.org/W1492019883","https://openalex.org/W1529304102","https://openalex.org/W1536564409","https://openalex.org/W1572085513","https://openalex.org/W1585971644","https://openalex.org/W1591319746","https://openalex.org/W1856176155","https://openalex.org/W1965638741","https://openalex.org/W1969874300","https://openalex.org/W2000801758","https://openalex.org/W2064693219","https://openalex.org/W2079834329","https://openalex.org/W2090268225","https://openalex.org/W2099404643","https://openalex.org/W2105049678","https://openalex.org/W2111394443","https://openalex.org/W2112482891","https://openalex.org/W2113798864","https://openalex.org/W2114067856","https://openalex.org/W2127324789","https://openalex.org/W2134855419","https://openalex.org/W2135736783","https://openalex.org/W2136285318","https://openalex.org/W2137249790","https://openalex.org/W2139600911","https://openalex.org/W2140311411","https://openalex.org/W2146147106","https://openalex.org/W2154109468","https://openalex.org/W2162310026","https://openalex.org/W2162921448","https://openalex.org/W2167639788","https://openalex.org/W2171641226","https://openalex.org/W2505443766","https://openalex.org/W4242970092","https://openalex.org/W4244894488","https://openalex.org/W4245987756","https://openalex.org/W4252742548","https://openalex.org/W4386313596","https://openalex.org/W6676870935"],"related_works":["https://openalex.org/W2115688358","https://openalex.org/W1503212777","https://openalex.org/W2072728786","https://openalex.org/W2066454338","https://openalex.org/W2146636354","https://openalex.org/W1994316441","https://openalex.org/W2172096703","https://openalex.org/W2132832499","https://openalex.org/W1989702012","https://openalex.org/W4242404469"],"abstract_inverted_index":{"Retargetable":[0],"C":[1,191],"compilers":[2,42],"are":[3,107,132],"currently":[4],"widely":[5],"used":[6],"to":[7,17,40,47,68,99,134,140,204,216],"quickly":[8,178],"obtain":[9],"compiler":[10],"support":[11,110],"for":[12,91,195],"new":[13],"embedded":[14,89],"processors":[15,90,197],"and":[16,118,155,177,208],"perform":[18],"early":[19],"processor":[20],"architecture":[21,137],"exploration.":[22],"A":[23],"partially":[24],"inherent":[25],"problem":[26,55],"of":[27,50,72,115,145],"the":[28,34,48,135,142,148,152,156,200,217],"retargetable":[29,62,179,190],"compilation":[30],"approach,":[31],"though,":[32],"is":[33,97,166,185],"limited":[35,113],"code":[36,45,63,181,212],"quality":[37,213],"as":[38],"compared":[39],"hand-written":[41],"or":[43],"assembly":[44],"due":[46],"lack":[49],"dedicated":[51],"optimizations":[52],"techniques.":[53],"This":[54,75],"can":[56],"be":[57,100],"circumvented":[58],"by":[59],"designing":[60],"flexible,":[61],"optimization":[64,96,154,182],"techniques":[65,126],"that":[66,184,199,209],"apply":[67],"a":[69,85,101,112,162],"certain":[70],"range":[71],"target":[73,79,206],"architectures.":[74],"article":[76],"focuses":[77],"on":[78],"machines":[80,207],"with":[81],"SIMD":[82,95,105,136,153,180],"instruction":[83],"support,":[84],"common":[86],"feature":[87],"in":[88,138,147,161],"multimedia":[92],"applications.":[93],"However,":[94],"known":[98],"difficult":[102],"task":[103],"since":[104],"architectures":[106],"largely":[108],"nonuniform,":[109],"only":[111],"set":[114],"data":[116],"types":[117],"impose":[119],"several":[120],"memory":[121],"alignment":[122],"constraints.":[123],"Additionally,":[124],"such":[125],"require":[127],"complicated":[128],"loop":[129,158],"transformations,":[130],"which":[131],"tailored":[133],"order":[139],"exhibit":[141],"necessary":[143],"amount":[144],"parallelism":[146],"code.":[149],"Thus,":[150],"integrating":[151],"required":[157],"transformations":[159],"together":[160],"single":[163],"retargeting":[164],"formalism":[165],"an":[167,175,188],"ambitious":[168],"challenge.":[169],"In":[170],"this":[171],"article,":[172],"we":[173],"present":[174],"efficient":[176],"framework":[183],"integrated":[186],"into":[187],"industrial":[189],"compiler.":[192],"Experimental":[193],"results":[194],"different":[196],"demonstrate":[198],"proposed":[201],"technique":[202],"applies":[203],"real-life":[205],"it":[210],"produces":[211],"improvements":[214],"close":[215],"theoretical":[218],"limit.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
