{"id":"https://openalex.org/W2292182532","doi":"https://doi.org/10.1145/2838735","title":"Automatic Vectorization of Interleaved Data Revisited","display_name":"Automatic Vectorization of Interleaved Data Revisited","publication_year":2015,"publication_date":"2015-12-08","ids":{"openalex":"https://openalex.org/W2292182532","doi":"https://doi.org/10.1145/2838735","mag":"2292182532"},"language":"en","primary_location":{"id":"doi:10.1145/2838735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2838735","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2838735?download=true","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/10.1145/2838735?download=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010687192","display_name":"Andrew Anderson","orcid":"https://orcid.org/0000-0002-4357-4739"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Andrew Anderson","raw_affiliation_strings":["Lero, Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Lero, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007782699","display_name":"Avinash Malik","orcid":"https://orcid.org/0000-0002-7524-8292"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Avinash Malik","raw_affiliation_strings":["University of Auckland, Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003800161","display_name":"David Gregg","orcid":"https://orcid.org/0000-0003-3782-4612"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"David Gregg","raw_affiliation_strings":["Lero, Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Lero, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010687192"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":3.975,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93975166,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":"4","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":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":0.9976000189781189,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9923999905586243,"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":0.8857709765434265},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7290837168693542},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6742821931838989},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.6107949614524841},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.555781364440918},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5352001786231995},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4995722770690918},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.42004841566085815},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20303726196289062},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.15941524505615234},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1471196413040161}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8857709765434265},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7290837168693542},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6742821931838989},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.6107949614524841},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.555781364440918},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5352001786231995},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4995722770690918},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.42004841566085815},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20303726196289062},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.15941524505615234},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1471196413040161},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2838735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2838735","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2838735?download=true","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"}],"best_oa_location":{"id":"doi:10.1145/2838735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2838735","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2838735?download=true","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":[{"id":"https://openalex.org/G3252617548","display_name":null,"funder_award_id":"10/CE/I1855 to Lero","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G5357995293","display_name":null,"funder_award_id":"10/CE/I1855","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G7825098257","display_name":null,"funder_award_id":"12/IA/1381 and 10/CE/I1855","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G7863452979","display_name":null,"funder_award_id":"12/IA/1381","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2292182532.pdf","grobid_xml":"https://content.openalex.org/works/W2292182532.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1499418450","https://openalex.org/W1575008551","https://openalex.org/W1595548352","https://openalex.org/W1964031104","https://openalex.org/W1965061255","https://openalex.org/W1965638741","https://openalex.org/W1966324811","https://openalex.org/W1975594295","https://openalex.org/W1988425770","https://openalex.org/W1999102544","https://openalex.org/W2013156670","https://openalex.org/W2057455870","https://openalex.org/W2061055971","https://openalex.org/W2090268225","https://openalex.org/W2099404643","https://openalex.org/W2104378884","https://openalex.org/W2111394443","https://openalex.org/W2112482891","https://openalex.org/W2113558024","https://openalex.org/W2124273985","https://openalex.org/W2137857636","https://openalex.org/W2140080674","https://openalex.org/W2147654959","https://openalex.org/W2162310026","https://openalex.org/W2167639788","https://openalex.org/W2400908863","https://openalex.org/W3006518470","https://openalex.org/W3016220765","https://openalex.org/W3020952492","https://openalex.org/W3149591378","https://openalex.org/W4205855566","https://openalex.org/W4244894488","https://openalex.org/W4249596969"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W2979513934","https://openalex.org/W2351155539","https://openalex.org/W2013156670"],"abstract_inverted_index":{"Automatically":[0],"exploiting":[1],"short":[2],"vector":[3],"instructions":[4,18],"sets":[5],"(SSE,":[6],"AVX,":[7],"NEON)":[8],"is":[9,25,188],"a":[10,76,149],"critically":[11],"important":[12],"task":[13],"for":[14,64,85,118,191,197],"optimizing":[15],"compilers.":[16],"Vector":[17],"typically":[19],"work":[20,36],"best":[21],"on":[22,31,137,142,148,168,173,179,185],"data":[23,33,52,186],"that":[24,81,112],"contiguous":[26],"in":[27,129,145],"memory,":[28],"and":[29,39,121,140,171,194],"operating":[30],"non-contiguous":[32,48],"requires":[34],"additional":[35],"to":[37],"gather":[38],"scatter":[40],"the":[41,108,157],"data.":[42],"There":[43],"are":[44],"several":[45,95],"varieties":[46],"of":[47,78,107,135,151,166],"access,":[49],"including":[50],"interleaved":[51],"access.":[53],"An":[54],"existing":[55],"approach":[56,80,114,127],"used":[57],"by":[58,103],"GCC":[59,161],"generates":[60],"extremely":[61],"efficient":[62],"code":[63,84,134],"loops":[65],"with":[66],"power-of-2":[67,120],"interleaving":[68,89,123],"factors":[69],"(strides).":[70],"In":[71,91,176],"this":[72,79],"paper":[73],"we":[74,93],"propose":[75,94],"generalization":[77],"produces":[82],"similar":[83],"any":[86],"compile-time":[87],"constant":[88],"factor.":[90],"addition,":[92],"novel":[96],"program":[97],"transformations,":[98],"which":[99],"were":[100],"made":[101],"possible":[102],"our":[104,113,182],"generalized":[105],"representation":[106],"problem.":[109],"Experiments":[110],"show":[111],"achieves":[115,163],"significant":[116],"speedups":[117,131],"both":[119],"non--power-of-2":[122],"factors.":[124],"Our":[125],"vectorization":[126],"results":[128],"mean":[130,164],"over":[132,189,195],"scalar":[133,201],"1.77x":[136],"Intel":[138,143,169,174,180],"SSE":[139,170],"2.53x":[141],"AVX2":[144],"real-world":[146],"benchmarking":[147,178],"selection":[150],"BLAS":[152],"Level":[153],"1":[154],"routines.":[155],"On":[156],"same":[158],"benchmark":[159],"programs,":[160],"5.0":[162],"improvements":[165],"1.43x":[167],"1.30x":[172],"AVX2.":[175],"synthetic":[177],"SSE,":[181],"maximum":[183],"improvement":[184],"movement":[187],"4x":[190],"gathering":[192],"operations":[193,199],"6x":[196],"scattering":[198],"versus":[200],"code.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}
