{"id":"https://openalex.org/W4409132036","doi":"https://doi.org/10.1109/hpec62836.2024.10938481","title":"Comparison of Vectorization Capabilities of Different Compilers for X86 and ARM CPUs","display_name":"Comparison of Vectorization Capabilities of Different Compilers for X86 and ARM CPUs","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4409132036","doi":"https://doi.org/10.1109/hpec62836.2024.10938481"},"language":"en","primary_location":{"id":"doi:10.1109/hpec62836.2024.10938481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5084036124","display_name":"Nazmus Sakib","orcid":"https://orcid.org/0000-0002-0525-6342"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nazmus Sakib","raw_affiliation_strings":["Klipsch School of ECE, New Mexico State University,Las Cruces,NM,USA,88003"],"affiliations":[{"raw_affiliation_string":"Klipsch School of ECE, New Mexico State University,Las Cruces,NM,USA,88003","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041843809","display_name":"Tarun Prabhu","orcid":"https://orcid.org/0000-0001-7501-7227"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tarun Prabhu","raw_affiliation_strings":["Los Alamos National Laboratory,Los Alamos,NM,USA,87545"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory,Los Alamos,NM,USA,87545","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053809539","display_name":"Nandakishore Santhi","orcid":"https://orcid.org/0000-0002-4755-7821"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nandakishore Santhi","raw_affiliation_strings":["Los Alamos National Laboratory,Los Alamos,NM,USA,87545"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory,Los Alamos,NM,USA,87545","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010873686","display_name":"John Shalf","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Shalf","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,CA,USA,94720"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,CA,USA,94720","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087778749","display_name":"Abdel\u2010Hameed A. Badawy","orcid":"https://orcid.org/0000-0001-8027-1449"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdel-Hameed A. Badawy","raw_affiliation_strings":["Klipsch School of ECE, New Mexico State University,Las Cruces,NM,USA,88003"],"affiliations":[{"raw_affiliation_string":"Klipsch School of ECE, New Mexico State University,Las Cruces,NM,USA,88003","institution_ids":["https://openalex.org/I10052268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5084036124"],"corresponding_institution_ids":["https://openalex.org/I10052268"],"apc_list":null,"apc_paid":null,"fwci":0.5139,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70213563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9484000205993652,"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":0.9484000205993652,"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":0.9323999881744385,"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/x86","display_name":"x86","score":0.9557090997695923},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8511888384819031},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7586044073104858},{"id":"https://openalex.org/keywords/arm-architecture","display_name":"ARM architecture","score":0.7195720672607422},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6872035264968872},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5304070711135864},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.38209056854248047},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3761295676231384},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1123209297657013}],"concepts":[{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.9557090997695923},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8511888384819031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586044073104858},{"id":"https://openalex.org/C26771161","wikidata":"https://www.wikidata.org/wiki/Q16980","display_name":"ARM architecture","level":2,"score":0.7195720672607422},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6872035264968872},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5304070711135864},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.38209056854248047},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3761295676231384},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1123209297657013}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec62836.2024.10938481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2013156670","https://openalex.org/W2072371063","https://openalex.org/W2314049432","https://openalex.org/W2543825515","https://openalex.org/W2741674747","https://openalex.org/W2979513934","https://openalex.org/W3024161604","https://openalex.org/W3140574618","https://openalex.org/W3216357191","https://openalex.org/W4312940613"],"related_works":["https://openalex.org/W2979513934","https://openalex.org/W2351155539","https://openalex.org/W2369102298","https://openalex.org/W2035419609","https://openalex.org/W3175617817","https://openalex.org/W343461076","https://openalex.org/W2090939166","https://openalex.org/W2020941354","https://openalex.org/W2601539487","https://openalex.org/W2544369712"],"abstract_inverted_index":{"Most":[0],"modern":[1],"processors":[2],"contain":[3],"vector":[4],"units":[5],"that":[6,67,116],"simultaneously":[7],"perform":[8],"the":[9,48,62,81,84,102,117,124,143,159,178],"same":[10],"arithmetic":[11],"operation":[12],"over":[13],"multiple":[14],"sets":[15],"of":[16,20,50,72,80,101,158],"operands.":[17],"The":[18],"ability":[19,49],"compilers":[21,52],"to":[22,28,53],"automatically":[23],"vectorize":[24,54,139],"code":[25,55,119,182],"is":[26,36,174],"critical":[27],"effectively":[29],"using":[30],"these":[31],"units.":[32],"Understanding":[33],"this":[34],"capability":[35],"important":[37],"for":[38],"anyone":[39],"writing":[40],"compute-intensive,":[41],"high-performance,":[42],"and":[43,58,93,111],"portable":[44],"code.":[45,74,126],"We":[46,60,114,145],"tested":[47],"several":[51],"on":[56,155,163,183],"x86":[57],"ARM.":[59],"used":[61],"TSVC2":[63],"suite,":[64],"with":[65],"modifications":[66],"made":[68],"it":[69],"more":[70],"representative":[71],"real-world":[73],"On":[75,96],"x86,":[76],"GCC":[77,98],"reported":[78,91,99,109],"54%":[79],"loops":[82,103],"in":[83],"suite":[85],"as":[86,104],"having":[87,105],"been":[88,106],"vectorized,":[89,107],"ICX":[90],"50%,":[92],"Clang,":[94,112],"46%.":[95],"ARM,":[97],"56%":[100],"ACFL":[108],"54%,":[110],"47%.":[113],"found":[115],"vectorized":[118,152],"did":[120],"not":[121,142],"always":[122],"outperform":[123],"unvectorized":[125],"In":[127],"some":[128],"cases,":[129],"given":[130,185],"two":[131,160],"very":[132],"similar":[133],"vectorizable":[134],"loops,":[135],"a":[136,150,153],"compiler":[137,151,173],"would":[138],"one":[140,157,172],"but":[141],"other.":[144],"also":[146],"report":[147],"cases":[148],"where":[149],"loop":[154],"only":[156],"platforms.":[161],"Based":[162],"our":[164],"experiments,":[165],"we":[166],"cannot":[167],"definitively":[168],"say":[169],"if":[170],"any":[171,184],"significantly":[175],"better":[176],"than":[177],"others":[179],"at":[180],"vectorizing":[181],"platform.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-04T07:04:00.330322","created_date":"2025-10-10T00:00:00"}
