{"id":"https://openalex.org/W2052870002","doi":"https://doi.org/10.1109/ipdpsw.2013.245","title":"Practical SIMD Vectorization Techniques for Intel® Xeon Phi Coprocessors","display_name":"Practical SIMD Vectorization Techniques for Intel® Xeon Phi Coprocessors","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2052870002","doi":"https://doi.org/10.1109/ipdpsw.2013.245","mag":"2052870002"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2013.245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2013.245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","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/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, California, USA","Mobile Comput. & Compilers Software & Service Group, Intel Corp., Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, California, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Mobile Comput. & Compilers Software & Service Group, Intel Corp., Santa Clara, CA, 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, California, USA","Mobile Comput. & Compilers Software & Service Group, Intel Corp., Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, California, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Mobile Comput. & Compilers Software & Service Group, Intel Corp., Santa Clara, CA, 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, Novosibirsk, Russia","Mobile Comput. & Compilers Software & Service Group, Intel Corp., Novosibirsk, Russia"],"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Novosibirsk, Russia","institution_ids":[]},{"raw_affiliation_string":"Mobile Comput. & Compilers Software & Service Group, Intel Corp., Novosibirsk, 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, California, USA","Mobile Comput. & Compilers Software & Service Group, Intel Corp., Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, California, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Mobile Comput. & Compilers Software & Service Group, Intel Corp., Santa Clara, CA, 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, Novosibirsk, Russia","Mobile Comput. & Compilers Software & Service Group, Intel Corp., Novosibirsk, Russia"],"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Novosibirsk, Russia","institution_ids":[]},{"raw_affiliation_string":"Mobile Comput. & Compilers Software & Service Group, Intel Corp., Novosibirsk, 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, California, USA","Mobile Comput. & Compilers Software & Service Group, Intel Corp., Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Santa Clara, California, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Mobile Comput. & Compilers Software & Service Group, Intel Corp., Santa Clara, CA, 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, Novosibirsk, Russia","Mobile Comput. & Compilers Software & Service Group, Intel Corp., Novosibirsk, Russia"],"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Novosibirsk, Russia","institution_ids":[]},{"raw_affiliation_string":"Mobile Comput. & Compilers Software & Service Group, Intel Corp., Novosibirsk, 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, Novosibirsk, Russia","Mobile Comput. & Compilers Software & Service Group, Intel Corp., Novosibirsk, Russia"],"affiliations":[{"raw_affiliation_string":"Mobile Computing and Compilers Software and Service Group, Intel Corporation, Novosibirsk, Russia","institution_ids":[]},{"raw_affiliation_string":"Mobile Comput. & Compilers Software & Service Group, Intel Corp., Novosibirsk, 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":null,"apc_paid":null,"fwci":6.17727342,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.97217524,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1149","last_page":"1158"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993000030517578,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9986000061035156,"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":0.952092170715332},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.8653064966201782},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.857223629951477},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7984930872917175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7520520687103271},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7497240900993347},{"id":"https://openalex.org/keywords/mmx","display_name":"MMX","score":0.5904667377471924},{"id":"https://openalex.org/keywords/intrinsics","display_name":"Intrinsics","score":0.5886589288711548},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.46015456318855286},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19157081842422485}],"concepts":[{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.952092170715332},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.8653064966201782},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.857223629951477},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7984930872917175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7520520687103271},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7497240900993347},{"id":"https://openalex.org/C85918911","wikidata":"https://www.wikidata.org/wiki/Q904336","display_name":"MMX","level":2,"score":0.5904667377471924},{"id":"https://openalex.org/C2908650547","wikidata":"https://www.wikidata.org/wiki/Q20999234","display_name":"Intrinsics","level":2,"score":0.5886589288711548},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.46015456318855286},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19157081842422485}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw.2013.245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2013.245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W92174080","https://openalex.org/W127897580","https://openalex.org/W1495550651","https://openalex.org/W1526547736","https://openalex.org/W1856176155","https://openalex.org/W1966324811","https://openalex.org/W1967002099","https://openalex.org/W1972547624","https://openalex.org/W2023636146","https://openalex.org/W2097572763","https://openalex.org/W2118031182","https://openalex.org/W2127324789","https://openalex.org/W2135736783","https://openalex.org/W2144643978","https://openalex.org/W2146558186","https://openalex.org/W3016220765","https://openalex.org/W3145971282","https://openalex.org/W3149591378","https://openalex.org/W6603776267","https://openalex.org/W6638901730","https://openalex.org/W6641587366","https://openalex.org/W6681144579"],"related_works":["https://openalex.org/W1908180445","https://openalex.org/W2213533160","https://openalex.org/W2467043670","https://openalex.org/W2035419609","https://openalex.org/W3203561460","https://openalex.org/W2065920469","https://openalex.org/W2120385681","https://openalex.org/W2052870002","https://openalex.org/W1939907483","https://openalex.org/W3105244973"],"abstract_inverted_index":{"Intel\u00ae":[0,8,54,73,87,94,132],"Xeon":[1,55,95,133],"Phi":[2,56,96,134],"coprocessor":[3],"is":[4,16,37,106],"based":[5],"on":[6,53,130],"the":[7,40,49,86,110,131],"Many":[9],"Integrated":[10],"Core":[11],"(Intel\u00ae":[12],"MIC)":[13],"architecture,":[14],"which":[15],"an":[17],"innovative":[18],"new":[19],"processor":[20],"architecture":[21],"that":[22,122],"combines":[23],"abundant":[24],"thread":[25],"parallelism":[26],"with":[27],"long":[28],"SIMD":[29,34,65,115],"vector":[30,35],"units.":[31],"Efficiently":[32],"exploiting":[33],"units":[36],"one":[38],"of":[39,48,100,113],"most":[41],"important":[42],"aspects":[43],"in":[44,85],"achieving":[45],"high":[46],"performance":[47,111,119,128],"application":[50,104],"code":[51],"running":[52],"coprocessors.":[57,97],"In":[58],"this":[59],"paper,":[60],"we":[61,123],"present":[62],"several":[63,103],"practical":[64],"vectorization":[66,83,116],"techniques":[67],"such":[68],"as":[69],"less-than-full-vector":[70],"loop":[71],"vectorization,":[72],"MIC":[74],"specific":[75],"alignment":[76],"optimization,":[77],"and":[78,89],"small":[79],"matrix":[80],"transpose/multiplication":[81],"2-D":[82],"implemented":[84],"C/C++":[88],"Fortran":[90],"production":[91],"compilers":[92],"for":[93],"A":[98],"set":[99],"workloads":[101],"from":[102],"domains":[105],"employed":[107],"to":[108,126],"conduct":[109],"study":[112],"our":[114],"techniques.":[117],"The":[118],"results":[120],"show":[121],"achieved":[124],"up":[125],"12.5x":[127],"gain":[129],"coprocessor.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}