{"id":"https://openalex.org/W1939907483","doi":"https://doi.org/10.1155/2015/269764","title":"Effective SIMD Vectorization for Intel Xeon Phi Coprocessors","display_name":"Effective SIMD Vectorization for Intel Xeon Phi Coprocessors","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1939907483","doi":"https://doi.org/10.1155/2015/269764","mag":"1939907483"},"language":"en","primary_location":{"id":"doi:10.1155/2015/269764","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2015/269764","pdf_url":"https://downloads.hindawi.com/journals/sp/2015/269764.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/journals/sp/2015/269764.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101131112","display_name":"Xinmin Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinmin Tian","raw_affiliation_strings":["Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, CA 95054, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, CA 95054, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063368240","display_name":"Hideki Saito","orcid":"https://orcid.org/0009-0004-5529-7048"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hideki Saito","raw_affiliation_strings":["Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, CA 95054, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, CA 95054, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111510122","display_name":"Serguei V. Preis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Serguei V. Preis","raw_affiliation_strings":["Mobile Computing and Compilers Software and Service Group, Intel Corporation, 6/1 Prospect Akademika, Novosibirsk 125009, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, 6/1 Prospect Akademika, Novosibirsk 125009, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012628009","display_name":"Eric N. Garcia","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric N. Garcia","raw_affiliation_strings":["Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, CA 95054, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, CA 95054, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020308143","display_name":"Sergey S. Kozhukhov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergey S. Kozhukhov","raw_affiliation_strings":["Mobile Computing and Compilers Software and Service Group, Intel Corporation, 6/1 Prospect Akademika, Novosibirsk 125009, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, 6/1 Prospect Akademika, Novosibirsk 125009, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018404027","display_name":"Matt Masten","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matt Masten","raw_affiliation_strings":["Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, CA 95054, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, CA 95054, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071285159","display_name":"Aleksei G. Cherkasov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksei G. Cherkasov","raw_affiliation_strings":["Mobile Computing and Compilers Software and Service Group, Intel Corporation, 6/1 Prospect Akademika, Novosibirsk 125009, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, 6/1 Prospect Akademika, Novosibirsk 125009, Russia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109165250","display_name":"N. V. Panchenko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolay Panchenko","raw_affiliation_strings":["Mobile Computing and Compilers Software and Service Group, Intel Corporation, 6/1 Prospect Akademika, Novosibirsk 125009, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, 6/1 Prospect Akademika, Novosibirsk 125009, Russia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101131112"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":{"value":1800,"currency":"USD","value_usd":1800},"apc_paid":{"value":1800,"currency":"USD","value_usd":1800},"fwci":4.942,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95173128,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2015","issue":null,"first_page":"1","last_page":"14"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.998199999332428,"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":0.9975000023841858,"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/xeon-phi","display_name":"Xeon Phi","score":0.9376044273376465},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.8939164876937866},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.883916974067688},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.7966364622116089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7501220107078552},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6950417757034302},{"id":"https://openalex.org/keywords/mmx","display_name":"MMX","score":0.6109404563903809},{"id":"https://openalex.org/keywords/intrinsics","display_name":"Intrinsics","score":0.5281650424003601},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5202361345291138},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4556758999824524},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12090519070625305}],"concepts":[{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.9376044273376465},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.8939164876937866},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.883916974067688},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.7966364622116089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501220107078552},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6950417757034302},{"id":"https://openalex.org/C85918911","wikidata":"https://www.wikidata.org/wiki/Q904336","display_name":"MMX","level":2,"score":0.6109404563903809},{"id":"https://openalex.org/C2908650547","wikidata":"https://www.wikidata.org/wiki/Q20999234","display_name":"Intrinsics","level":2,"score":0.5281650424003601},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5202361345291138},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4556758999824524},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12090519070625305}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/2015/269764","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2015/269764","pdf_url":"https://downloads.hindawi.com/journals/sp/2015/269764.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:48509dac13b948859da024f2e94e0088","is_oa":false,"landing_page_url":"https://doaj.org/article/48509dac13b948859da024f2e94e0088","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 2015 (2015)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2015/269764","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2015/269764","pdf_url":"https://downloads.hindawi.com/journals/sp/2015/269764.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1939907483.pdf","grobid_xml":"https://content.openalex.org/works/W1939907483.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W92174080","https://openalex.org/W127897580","https://openalex.org/W624975885","https://openalex.org/W1495550651","https://openalex.org/W1526547736","https://openalex.org/W1966324811","https://openalex.org/W1967002099","https://openalex.org/W1972547624","https://openalex.org/W2023636146","https://openalex.org/W2079834329","https://openalex.org/W2097572763","https://openalex.org/W2111394443","https://openalex.org/W2118031182","https://openalex.org/W2127324789","https://openalex.org/W2135736783","https://openalex.org/W2144643978","https://openalex.org/W2146558186","https://openalex.org/W2147654959"],"related_works":["https://openalex.org/W1908180445","https://openalex.org/W2213533160","https://openalex.org/W2035419609","https://openalex.org/W3203561460","https://openalex.org/W4252450863","https://openalex.org/W2467043670","https://openalex.org/W2065920469","https://openalex.org/W2120385681","https://openalex.org/W1939907483","https://openalex.org/W2052870002"],"abstract_inverted_index":{"Efficiently":[0],"exploiting":[1],"SIMD":[2,33,83,116],"vector":[3],"units":[4],"is":[5,74],"one":[6],"of":[7,16,68,81,115],"the":[8,17,54,78,99,112],"most":[9],"important":[10],"aspects":[11],"in":[12,53],"achieving":[13],"high":[14],"performance":[15,79,87,96,109],"application":[18,72],"code":[19],"running":[20],"on":[21,98],"Intel":[22,41,55,62,100],"Xeon":[23,63,101],"Phi":[24,64,102],"coprocessors.":[25,65],"In":[26],"this":[27],"paper,":[28],"we":[29,91],"present":[30],"several":[31,71],"effective":[32],"vectorization":[34,51,84,117],"techniques":[35],"such":[36],"as":[37],"less-than-full-vector":[38],"loop":[39],"vectorization,":[40],"MIC":[42],"specific":[43],"alignment":[44],"optimization,":[45],"and":[46,57,118],"small":[47],"matrix":[48],"transpose/multiplication":[49],"2D":[50],"implemented":[52],"C/C++":[56],"Fortran":[58],"production":[59],"compilers":[60],"for":[61],"A":[66],"set":[67],"workloads":[69],"from":[70,111],"domains":[73],"employed":[75],"to":[76,94],"conduct":[77],"study":[80],"our":[82],"techniques.":[85],"The":[86],"results":[88],"show":[89],"that":[90],"achieved":[92],"up":[93],"12.5x":[95],"gain":[97],"coprocessor.":[103],"We":[104],"also":[105],"demonstrate":[106],"a":[107],"2000x":[108],"speedup":[110],"seamless":[113],"integration":[114],"parallelization.":[119]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}