{"id":"https://openalex.org/W4248277950","doi":"https://doi.org/10.1002/cpe.1333","title":"Improving performance of optimized kernels through fast instantiations of templates","display_name":"Improving performance of optimized kernels through fast instantiations of templates","publication_year":2008,"publication_date":"2008-07-22","ids":{"openalex":"https://openalex.org/W4248277950","doi":"https://doi.org/10.1002/cpe.1333"},"language":"en","primary_location":{"id":"doi:10.1002/cpe.1333","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cpe.1333","pdf_url":null,"source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-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/A5100753305","display_name":"Minhaj Ahmad Khan","orcid":"https://orcid.org/0000-0002-2375-7829"},"institutions":[{"id":"https://openalex.org/I4210165330","display_name":"Institut Lavoisier de Versailles","ror":"https://ror.org/05mzd8v39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4210128300","https://openalex.org/I4210165330"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Minhaj Ahmad Khan","raw_affiliation_strings":["University of Versailles, Versailles, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Versailles, Versailles, France","institution_ids":["https://openalex.org/I4210165330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074051956","display_name":"Henri\u2010Pierre Charles","orcid":"https://orcid.org/0000-0002-0119-0446"},"institutions":[{"id":"https://openalex.org/I4210165330","display_name":"Institut Lavoisier de Versailles","ror":"https://ror.org/05mzd8v39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4210128300","https://openalex.org/I4210165330"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"H.\u2010P. Charles","raw_affiliation_strings":["University of Versailles, Versailles, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Versailles, Versailles, France","institution_ids":["https://openalex.org/I4210165330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030777320","display_name":"Denis Barthou","orcid":"https://orcid.org/0009-0000-8547-5395"},"institutions":[{"id":"https://openalex.org/I4210165330","display_name":"Institut Lavoisier de Versailles","ror":"https://ror.org/05mzd8v39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4210128300","https://openalex.org/I4210165330"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"D. Barthou","raw_affiliation_strings":["University of Versailles, Versailles, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Versailles, Versailles, France","institution_ids":["https://openalex.org/I4210165330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100753305"],"corresponding_institution_ids":["https://openalex.org/I4210165330"],"apc_list":{"value":4740,"currency":"USD","value_usd":4740},"apc_paid":null,"fwci":1.0261,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82723998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"21","issue":"1","first_page":"59","last_page":"70"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9898999929428101,"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":0.9868000149726868,"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/computer-science","display_name":"Computer science","score":0.8748727440834045},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8668516278266907},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.8546351790428162},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.8478958606719971},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7345761060714722},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.702459454536438},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6876435279846191},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5534263253211975},{"id":"https://openalex.org/keywords/just-in-time-compilation","display_name":"Just-in-time compilation","score":0.4744488000869751},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.456932008266449},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.44278424978256226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8748727440834045},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8668516278266907},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.8546351790428162},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.8478958606719971},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7345761060714722},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.702459454536438},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6876435279846191},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5534263253211975},{"id":"https://openalex.org/C76782552","wikidata":"https://www.wikidata.org/wiki/Q110546","display_name":"Just-in-time compilation","level":3,"score":0.4744488000869751},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.456932008266449},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.44278424978256226},{"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:10.1002/cpe.1333","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cpe.1333","pdf_url":null,"source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1486688036","https://openalex.org/W1604252617","https://openalex.org/W1797198873","https://openalex.org/W1978506930","https://openalex.org/W2002181967","https://openalex.org/W2019722731","https://openalex.org/W2048423324","https://openalex.org/W2102182691","https://openalex.org/W2105528304","https://openalex.org/W2136422035","https://openalex.org/W4232576303","https://openalex.org/W4248710586","https://openalex.org/W4251073284"],"related_works":["https://openalex.org/W2371266106","https://openalex.org/W2014874874","https://openalex.org/W2117382851","https://openalex.org/W3006505070","https://openalex.org/W2382449560","https://openalex.org/W2767298477","https://openalex.org/W2110432562","https://openalex.org/W3153841236","https://openalex.org/W2485116099","https://openalex.org/W2510797"],"abstract_inverted_index":{"Abstract":[0],"To":[1],"fully":[2],"exploit":[3],"the":[4,13,18,21,39,50,54,79,116],"instruction\u2010level":[5],"parallelism":[6],"offered":[7],"by":[8,46],"modern":[9],"processors,":[10],"compilers":[11],"need":[12],"necessary":[14],"information":[15],"available":[16],"during":[17],"execution":[19],"of":[20,41,49,56,81,87,101,106,141,166],"program.":[22],"This":[23],"advocates":[24],"for":[25,36,66,77],"iterative":[26,57],"or":[27],"dynamic":[28,31,150],"compilation.":[29],"Unfortunately,":[30],"compilation":[32,42,58],"is":[33],"suitable":[34],"only":[35],"applications":[37],"where":[38],"cost":[40,55],"may":[43],"be":[44,63],"amortized":[45],"multiple":[47],"invocations":[48],"same":[51],"code.":[52],"Similarly,":[53],"makes":[59],"it":[60],"impractical":[61],"to":[62],"widely":[64],"used":[65],"performance":[67,80],"improvement.":[68],"In":[69],"this":[70],"article,":[71],"we":[72],"suggest":[73],"a":[74,98,122],"novel":[75],"approach":[76],"improving":[78],"mathematical":[82],"kernels":[83,165],"through":[84,126],"fast":[85],"instantiations":[86,105,118],"templates.":[88],"Optimized":[89],"templates":[90,108],"are":[91,109,119],"generated":[92],"at":[93,111,132,145],"static":[94,112,146],"compile":[95,113,147,151],"time":[96,148],"with":[97,121,170],"limited":[99],"number":[100],"compilations.":[102],"The":[103,153],"initial":[104],"these":[107],"performed":[110,120,157],"time,":[114],"and":[115,149,168,172],"runtime":[117],"very":[123],"small":[124],"overhead":[125,143],"specialized":[127],"data,":[128],"requiring":[129],"no":[130],"computations":[131],"runtime.":[133],"It":[134],"represents":[135],"an":[136,159],"effective":[137],"solution":[138],"in":[139],"terms":[140],"reduced":[142],"incurring":[144],"time.":[152],"experiments":[154],"have":[155],"been":[156],"on":[158],"Itanium\u2010II":[160],"architecture":[161],"using":[162],"highly":[163],"optimized":[164],"ATLAS":[167],"FFTW":[169],"icc":[171],"gcc":[173],"compilers.":[174],"Copyright":[175],"\u00a9":[176],"2008":[177],"John":[178],"Wiley":[179],"&amp;":[180],"Sons,":[181],"Ltd.":[182]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
