{"id":"https://openalex.org/W4385175635","doi":"https://doi.org/10.1145/3631709","title":"Autovesk: Automatic Vectorized Code Generation from Unstructured Static Kernels Using Graph Transformations","display_name":"Autovesk: Automatic Vectorized Code Generation from Unstructured Static Kernels Using Graph Transformations","publication_year":2023,"publication_date":"2023-11-09","ids":{"openalex":"https://openalex.org/W4385175635","doi":"https://doi.org/10.1145/3631709"},"language":"en","primary_location":{"id":"doi:10.1145/3631709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3631709","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3631709","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":true,"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":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3631709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046357098","display_name":"Hayfa Tayeb","orcid":"https://orcid.org/0000-0002-1634-6124"},"institutions":[{"id":"https://openalex.org/I4210100283","display_name":"Laboratoire des Sciences de l'Ing\u00e9nieur, de l'Informatique et de l'Imagerie","ror":"https://ror.org/00k4e5n71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2801509770","https://openalex.org/I4210095849","https://openalex.org/I4210100283","https://openalex.org/I4210159245","https://openalex.org/I68947357"]},{"id":"https://openalex.org/I4210146719","display_name":"Central Compilation & Translation Bureau","ror":"https://ror.org/0411yf357","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210146719"]},{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]}],"countries":["CN","FR"],"is_corresponding":false,"raw_author_name":"Hayfa Tayeb","raw_affiliation_strings":["ICube Lab, France and Inria, France and University of Strasbourg, France","Universit\u00e9 de Strasbourg","Compilation pour les Architectures MUlti-coeurS","Laboratoire des sciences de l'ing\u00e9nieur, de l'informatique et de l'imagerie"],"raw_orcid":"https://orcid.org/0000-0002-1634-6124","affiliations":[{"raw_affiliation_string":"ICube Lab, France and Inria, France and University of Strasbourg, France","institution_ids":["https://openalex.org/I68947357"]},{"raw_affiliation_string":"Universit\u00e9 de Strasbourg","institution_ids":["https://openalex.org/I68947357"]},{"raw_affiliation_string":"Compilation pour les Architectures MUlti-coeurS","institution_ids":["https://openalex.org/I4210146719"]},{"raw_affiliation_string":"Laboratoire des sciences de l'ing\u00e9nieur, de l'informatique et de l'imagerie","institution_ids":["https://openalex.org/I4210100283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104622824","display_name":"Ludovic Paillat","orcid":"https://orcid.org/0000-0002-5428-8834"},"institutions":[{"id":"https://openalex.org/I4210100283","display_name":"Laboratoire des Sciences de l'Ing\u00e9nieur, de l'Informatique et de l'Imagerie","ror":"https://ror.org/00k4e5n71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2801509770","https://openalex.org/I4210095849","https://openalex.org/I4210100283","https://openalex.org/I4210159245","https://openalex.org/I68947357"]},{"id":"https://openalex.org/I4210146719","display_name":"Central Compilation & Translation Bureau","ror":"https://ror.org/0411yf357","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210146719"]},{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]}],"countries":["CN","FR"],"is_corresponding":false,"raw_author_name":"Ludovic Paillat","raw_affiliation_strings":["ICube Lab, France and Inria, France and University of Strasbourg, France","Laboratoire des sciences de l'ing\u00e9nieur, de l'informatique et de l'imagerie","Universit\u00e9 de Strasbourg","Compilation pour les Architectures MUlti-coeurS"],"raw_orcid":"https://orcid.org/0000-0002-5428-8834","affiliations":[{"raw_affiliation_string":"ICube Lab, France and Inria, France and University of Strasbourg, France","institution_ids":["https://openalex.org/I68947357"]},{"raw_affiliation_string":"Laboratoire des sciences de l'ing\u00e9nieur, de l'informatique et de l'imagerie","institution_ids":["https://openalex.org/I4210100283"]},{"raw_affiliation_string":"Universit\u00e9 de Strasbourg","institution_ids":["https://openalex.org/I68947357"]},{"raw_affiliation_string":"Compilation pour les Architectures MUlti-coeurS","institution_ids":["https://openalex.org/I4210146719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081443384","display_name":"B\u00e9renger Bramas","orcid":"https://orcid.org/0000-0003-0281-9709"},"institutions":[{"id":"https://openalex.org/I4210100283","display_name":"Laboratoire des Sciences de l'Ing\u00e9nieur, de l'Informatique et de l'Imagerie","ror":"https://ror.org/00k4e5n71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2801509770","https://openalex.org/I4210095849","https://openalex.org/I4210100283","https://openalex.org/I4210159245","https://openalex.org/I68947357"]},{"id":"https://openalex.org/I4210146719","display_name":"Central Compilation & Translation Bureau","ror":"https://ror.org/0411yf357","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210146719"]},{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]}],"countries":["CN","FR"],"is_corresponding":false,"raw_author_name":"B\u00e9renger Bramas","raw_affiliation_strings":["ICube Lab, France and Inria, France and University of Strasbourg, France","Compilation pour les Architectures MUlti-coeurS","Laboratoire des sciences de l'ing\u00e9nieur, de l'informatique et de l'imagerie","Universit\u00e9 de Strasbourg"],"raw_orcid":"https://orcid.org/0000-0003-0281-9709","affiliations":[{"raw_affiliation_string":"ICube Lab, France and Inria, France and University of Strasbourg, France","institution_ids":["https://openalex.org/I68947357"]},{"raw_affiliation_string":"Compilation pour les Architectures MUlti-coeurS","institution_ids":["https://openalex.org/I4210146719"]},{"raw_affiliation_string":"Laboratoire des sciences de l'ing\u00e9nieur, de l'informatique et de l'imagerie","institution_ids":["https://openalex.org/I4210100283"]},{"raw_affiliation_string":"Universit\u00e9 de Strasbourg","institution_ids":["https://openalex.org/I68947357"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4417,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80486692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"21","issue":"1","first_page":"1","last_page":"25"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9884999990463257,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8930412530899048},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7387522459030151},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.721413254737854},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6908960342407227},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.6301387548446655},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.5754568576812744},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4778032898902893},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.4180656969547272},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.41398561000823975},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4125111997127533},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.35789158940315247},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.3226172626018524},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23955532908439636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8930412530899048},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7387522459030151},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.721413254737854},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6908960342407227},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6301387548446655},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.5754568576812744},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4778032898902893},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.4180656969547272},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.41398561000823975},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4125111997127533},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35789158940315247},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3226172626018524},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23955532908439636},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3631709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3631709","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3631709","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":true,"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:HAL:hal-03914178v3","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03914178","pdf_url":"https://inria.hal.science/hal-03914178v3/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://dl.acm.org/doi/10.1145/3631709","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1145/3631709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3631709","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3631709","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":true,"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":[{"id":"https://openalex.org/G4405971636","display_name":"GW4 Tier-2 HPC Centre for Advanced Architectures","funder_award_id":"EP/T022078/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320331","display_name":"Met Office","ror":"https://ror.org/01ch2yn61"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"},{"id":"https://openalex.org/F4320323712","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385175635.pdf","grobid_xml":"https://content.openalex.org/works/W4385175635.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1530670596","https://openalex.org/W2069504277","https://openalex.org/W2070590009","https://openalex.org/W2078862445","https://openalex.org/W2090268225","https://openalex.org/W2094969361","https://openalex.org/W2099404643","https://openalex.org/W2111394443","https://openalex.org/W2118031182","https://openalex.org/W2135736783","https://openalex.org/W2157273783","https://openalex.org/W2191880228","https://openalex.org/W2250964545","https://openalex.org/W2292182532","https://openalex.org/W2412026823","https://openalex.org/W2488840986","https://openalex.org/W2520139353","https://openalex.org/W2566431638","https://openalex.org/W2754764408","https://openalex.org/W2782176700","https://openalex.org/W2789135440","https://openalex.org/W2791658442","https://openalex.org/W2898106867","https://openalex.org/W2912841518","https://openalex.org/W2914479353","https://openalex.org/W3008658471","https://openalex.org/W3152824079","https://openalex.org/W4242726609","https://openalex.org/W4245767887","https://openalex.org/W4246945770","https://openalex.org/W4249544322","https://openalex.org/W4300721631","https://openalex.org/W4307380766"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W2366442643","https://openalex.org/W2021715972","https://openalex.org/W2090268225","https://openalex.org/W75461624","https://openalex.org/W2766828645"],"abstract_inverted_index":{"Leveraging":[0],"the":[1,39,123,132,149],"SIMD":[2],"capability":[3],"of":[4,14,111,127,134,151],"modern":[5,62],"CPU":[6],"architectures":[7],"is":[8],"mandatory":[9],"to":[10,121,173],"take":[11],"full":[12],"advantage":[13],"their":[15],"increased":[16],"performance.":[17],"To":[18],"exploit":[19],"this":[20,37,81],"capability,":[21],"binary":[22],"executables":[23],"must":[24],"be":[25],"vectorized,":[26],"either":[27],"manually":[28],"by":[29,33],"developers":[30],"or":[31,125],"automatically":[32,90],"a":[34,52,78,85,109,115],"tool.":[35],"For":[36],"reason,":[38],"compilation":[40],"research":[41],"community":[42],"has":[43],"developed":[44],"several":[45],"strategies":[46],"for":[47,66],"transforming":[48],"scalar":[49,95,112],"code":[50,93,154],"into":[51,114],"vectorized":[53,92,116,153],"implementation.":[54],"However,":[55],"most":[56],"existing":[57],"automatic":[58,161],"vectorization":[59,162],"techniques":[60],"in":[61],"compilers":[63],"are":[64],"designed":[65],"regular":[67],"codes,":[68],"leaving":[69],"irregular":[70,99,177],"applications":[71],"with":[72],"non-contiguous":[73],"data":[74,100],"access":[75,101],"patterns":[76],"at":[77],"disadvantage.":[79],"In":[80],"article,":[82],"we":[83,130],"present":[84],"new":[86],"tool,":[87],"Autovesk,":[88],"that":[89],"generates":[91],"from":[94],"code,":[96],"specifically":[97],"targeting":[98],"patterns.":[102],"We":[103,147,164],"describe":[104],"how":[105],"our":[106,135],"method":[107],"transforms":[108],"graph":[110],"instructions":[113],"one,":[117],"using":[118,141],"different":[119],"heuristics":[120],"reduce":[122],"number":[124],"cost":[126],"instructions.":[128],"Finally,":[129],"demonstrate":[131],"effectiveness":[133],"approach":[136],"on":[137,168,176],"various":[138],"computational":[139],"kernels":[140,170],"Intel":[142,160],"AVX-512":[143],"and":[144,159,171],"ARM":[145],"SVE.":[146],"compare":[148],"speedups":[150,175],"Autovesk":[152],"over":[155],"GCC,":[156],"Clang":[157],"LLVM,":[158],"optimizations.":[163],"achieve":[165],"competitive":[166],"results":[167],"linear":[169],"up":[172],"11\u00d7":[174],"kernels.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
