{"id":"https://openalex.org/W2064441385","doi":"https://doi.org/10.1145/2086696.2086729","title":"Using machine learning to improve automatic vectorization","display_name":"Using machine learning to improve automatic vectorization","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2064441385","doi":"https://doi.org/10.1145/2086696.2086729","mag":"2064441385"},"language":"en","primary_location":{"id":"doi:10.1145/2086696.2086729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2086696.2086729","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2086696.2086729","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2086696.2086729","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062877582","display_name":"Kevin Stock","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Stock","raw_affiliation_strings":["The Ohio State University","the Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"the Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040769038","display_name":"Louis-No\u00ebl Pouchet","orcid":"https://orcid.org/0000-0001-5103-3097"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-No\u00ebl Pouchet","raw_affiliation_strings":["The Ohio State University","the Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"the Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["The Ohio State University","the Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"the Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.8967,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.90728232,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"8","issue":"4","first_page":"1","last_page":"23"},"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":0.9865999817848206,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9710999727249146,"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/vectorization","display_name":"Vectorization (mathematics)","score":0.9027104377746582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8904253244400024},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8022737503051758},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7691527605056763},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7003248929977417},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5924715995788574},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5309904217720032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5036386847496033},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5014581680297852},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44454336166381836},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37365972995758057},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.37198883295059204},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25957316160202026},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.1806415617465973},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.1002032458782196}],"concepts":[{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.9027104377746582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8904253244400024},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8022737503051758},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7691527605056763},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7003248929977417},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5924715995788574},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5309904217720032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5036386847496033},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5014581680297852},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44454336166381836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37365972995758057},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.37198883295059204},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25957316160202026},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.1806415617465973},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.1002032458782196},{"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:10.1145/2086696.2086729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2086696.2086729","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2086696.2086729","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/2086696.2086729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2086696.2086729","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2086696.2086729","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[{"score":0.5299999713897705,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1372563335","display_name":"Customizable Domain-Specific Computing","funder_award_id":"0926127","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1958599382","display_name":"Collaborative Research:  An Environment for High-Productivity High-Performance Computing using GPUs/Accelerators","funder_award_id":"0926688","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G21270963","display_name":"Collaborative Research:   CPA-CPL-T:  An Effective Automatic Parallelization Framework for Multi-Core Architectures","funder_award_id":"0811781","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2778365179","display_name":null,"funder_award_id":"8.12E+12","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6586304796","display_name":null,"funder_award_id":"CCF-0926127","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G6865471441","display_name":null,"funder_award_id":"CCF-0926127","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/F4320309374","display_name":"Ohio State University","ror":"https://ror.org/00rs6vg23"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2064441385.pdf","grobid_xml":"https://content.openalex.org/works/W2064441385.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1499418450","https://openalex.org/W1509875415","https://openalex.org/W1584675441","https://openalex.org/W1665412445","https://openalex.org/W1997375049","https://openalex.org/W2005985523","https://openalex.org/W2063249715","https://openalex.org/W2064508949","https://openalex.org/W2090268225","https://openalex.org/W2093135480","https://openalex.org/W2095776265","https://openalex.org/W2099404643","https://openalex.org/W2100933152","https://openalex.org/W2108737583","https://openalex.org/W2111394443","https://openalex.org/W2112482891","https://openalex.org/W2115089829","https://openalex.org/W2118031182","https://openalex.org/W2119691711","https://openalex.org/W2127324789","https://openalex.org/W2137249790","https://openalex.org/W2142079700","https://openalex.org/W2143124065","https://openalex.org/W2156768443","https://openalex.org/W2157273783","https://openalex.org/W2158626113","https://openalex.org/W2159846564","https://openalex.org/W2166061155","https://openalex.org/W2168519934","https://openalex.org/W2170753802","https://openalex.org/W2171539112","https://openalex.org/W3146578712","https://openalex.org/W4244894488","https://openalex.org/W4245503759","https://openalex.org/W6676870935","https://openalex.org/W6684171947"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W3092174096","https://openalex.org/W1559264847","https://openalex.org/W3205799311","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W2979513934","https://openalex.org/W4300860486"],"abstract_inverted_index":{"Automatic":[0],"vectorization":[1,165],"is":[2,15,49],"critical":[3],"to":[4,74,90,99,138,162,178],"enhancing":[5],"performance":[6,93],"of":[7,24,36,46,53,58,94,107,132,154,169,190,196],"compute-intensive":[8],"programs":[9],"on":[10,116,129,166,193],"modern":[11],"processors.":[12],"However,":[13],"there":[14],"much":[16],"room":[17],"for":[18],"improvement":[19,202],"over":[20,180,203],"the":[21,44,51,54,76,92,108,120,147,152,155,188,191],"auto-vectorization":[22],"capabilities":[23],"current":[25],"production":[26],"compilers":[27,70],"through":[28],"careful":[29],"vector-code":[30],"synthesis":[31],"that":[32,102],"utilizes":[33],"a":[34,61,130,167,194],"variety":[35,168],"loop":[37],"transformations":[38,47,59],"(e.g.,":[39],"unroll-and-jam,":[40],"interchange,":[41],"etc.).":[42],"As":[43],"set":[45],"considered":[48],"increased,":[50],"selection":[52],"most":[55],"effective":[56],"combination":[57],"becomes":[60],"significant":[62],"challenge:":[63],"Currently":[64],"used":[65,104,135],"cost":[66],"models":[67,89,114,125],"in":[68],"vectorizing":[69],"are":[71,126],"often":[72],"unable":[73],"identify":[75],"best":[77],"choices.":[78],"In":[79,97],"this":[80,84],"paper,":[81],"we":[82,110],"address":[83],"problem":[85],"using":[86,160],"machine":[87,112,156],"learning":[88,113,157],"predict":[91],"SIMD":[95],"codes.":[96],"contrast":[98],"existing":[100],"approaches":[101],"have":[103],"high-level":[105],"features":[106,117],"program,":[109],"develop":[111],"based":[115],"extracted":[118],"from":[119,146,176],"generated":[121,145],"assembly":[122],"code.":[123,149,184,205],"The":[124],"trained":[127],"offline":[128],"number":[131,195],"benchmarks":[133],"and":[134,199],"at":[136],"compile-time":[137],"discriminate":[139],"between":[140],"numerous":[141],"possible":[142],"vectorized":[143],"variants":[144],"input":[148],"We":[150,185],"demonstrate":[151],"effectiveness":[153,189],"model":[158,192],"by":[159],"it":[161],"guide":[163],"automatic":[164],"tensor":[170],"contraction":[171],"kernels,":[172],"with":[173],"improvements":[174],"ranging":[175],"2\u00d7":[177],"8\u00d7":[179],"Intel":[181],"ICC's":[182],"auto-vectorized":[183,204],"also":[186],"evaluate":[187],"stencil":[197],"computations":[198],"show":[200],"good":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}