{"id":"https://openalex.org/W2777814471","doi":"https://doi.org/10.1177/1094342017738352","title":"Offloading strategies for Stencil kernels on the KNC Xeon Phi architecture: Accuracy versus performance","display_name":"Offloading strategies for Stencil kernels on the KNC Xeon Phi architecture: Accuracy versus performance","publication_year":2017,"publication_date":"2017-11-07","ids":{"openalex":"https://openalex.org/W2777814471","doi":"https://doi.org/10.1177/1094342017738352","mag":"2777814471"},"language":"en","primary_location":{"id":"doi:10.1177/1094342017738352","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342017738352","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10251/169425","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050726441","display_name":"Mario Hern\u00e1ndez-Hern\u00e1ndez","orcid":"https://orcid.org/0000-0001-8330-4779"},"institutions":[{"id":"https://openalex.org/I3130105584","display_name":"Universidad Aut\u00f3noma de Guerrero","ror":"https://ror.org/054tbkd46","country_code":"MX","type":"education","lineage":["https://openalex.org/I3130105584"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Mario Hern\u00e1ndez","raw_affiliation_strings":["Facultad de Ingenier\u00eda, Universidad Aut\u00f3noma de Guerrero, Guerrero, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facultad de Ingenier\u00eda, Universidad Aut\u00f3noma de Guerrero, Guerrero, Mexico","institution_ids":["https://openalex.org/I3130105584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029097110","display_name":"Juan M. Cebri\u00e1n","orcid":"https://orcid.org/0000-0002-3731-9301"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan M Cebri\u00e1n","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC), Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC), Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088468258","display_name":"Jos\u00e9 M. Cecilia","orcid":"https://orcid.org/0000-0001-5648-214X"},"institutions":[{"id":"https://openalex.org/I68763199","display_name":"Universidad Cat\u00f3lica de Murcia","ror":"https://ror.org/05b1rsv17","country_code":"ES","type":"education","lineage":["https://openalex.org/I68763199"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 M Cecilia","raw_affiliation_strings":["Departamento de Ingenier\u00eda Inform\u00e1tica, Universidad Cat\u00f3lica San Antonio de Murcia, Murcia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda Inform\u00e1tica, Universidad Cat\u00f3lica San Antonio de Murcia, Murcia, Spain","institution_ids":["https://openalex.org/I68763199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070286319","display_name":"Jos\u00e9 M. Garc\u0131\u0301a","orcid":"https://orcid.org/0000-0002-6388-2835"},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 M Garc\u00eda","raw_affiliation_strings":["Departamento de Ingenier\u00eda y Tecnolog\u00eda de Computadores, Universidad de Murcia, Murcia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda y Tecnolog\u00eda de Computadores, Universidad de Murcia, Murcia, Spain","institution_ids":["https://openalex.org/I80180929"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050726441"],"corresponding_institution_ids":["https://openalex.org/I3130105584"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21933962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"2","first_page":"199","last_page":"207"},"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":0.9991000294685364,"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":0.9976999759674072,"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":0.8242724537849426},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7004415988922119},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6716247797012329},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.5339919924736023},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5138118863105774},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.503079354763031},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4749217927455902},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4719143211841583},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4247549772262573},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3924036920070648},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2688169479370117},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.1413922905921936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242724537849426},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7004415988922119},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6716247797012329},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.5339919924736023},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5138118863105774},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.503079354763031},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4749217927455902},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4719143211841583},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4247549772262573},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3924036920070648},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2688169479370117},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.1413922905921936},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/1094342017738352","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342017738352","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:riunet.upv.es:10251/169425","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/169425","pdf_url":null,"source":{"id":"https://openalex.org/S4306400639","display_name":"RiuNet (Universitat Polit\u00e8cnica de Val\u00e8ncia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:riunet.upv.es:10251/169425","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/169425","pdf_url":null,"source":{"id":"https://openalex.org/S4306400639","display_name":"RiuNet (Universitat Polit\u00e8cnica de Val\u00e8ncia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G3766983897","display_name":null,"funder_award_id":"TIN2015-66972-C5-3-R","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W227328431","https://openalex.org/W312001194","https://openalex.org/W348433680","https://openalex.org/W624975885","https://openalex.org/W996105196","https://openalex.org/W2043454202","https://openalex.org/W2049334739","https://openalex.org/W2281904070","https://openalex.org/W2496534597","https://openalex.org/W2499702955","https://openalex.org/W2604770745","https://openalex.org/W3022662367"],"related_works":["https://openalex.org/W2213533160","https://openalex.org/W3203561460","https://openalex.org/W4252450863","https://openalex.org/W2467043670","https://openalex.org/W187726678","https://openalex.org/W2269110805","https://openalex.org/W2051078434","https://openalex.org/W4294342484","https://openalex.org/W2022867993","https://openalex.org/W2682544458"],"abstract_inverted_index":{"The":[0],"ever-increasing":[1],"computational":[2,31,46],"requirements":[3,21],"of":[4,44,70,198],"HPC":[5],"and":[6,17,121,129,137],"service":[7],"provider":[8],"applications":[9],"are":[10,22,80,97],"becoming":[11],"a":[12,62,169,179],"great":[13],"challenge":[14],"for":[15,83,212],"hardware":[16,75],"software":[18],"designers.":[19],"These":[20],"reaching":[23],"levels":[24],"where":[25,85],"the":[26,45,50,74,106,134,141,160,204],"isolated":[27],"development":[28],"on":[29,123,156],"either":[30,110],"field":[32],"is":[33,48,60],"not":[34,61],"enough":[35],"to":[36,53,105,151],"deal":[37],"with":[38,126,159],"such":[39,102],"challenge.":[40],"A":[41],"holistic":[42],"view":[43],"thinking":[47],"therefore":[49],"only":[51],"way":[52],"success":[54],"in":[55],"real":[56],"scenarios.":[57],"However,":[58],"this":[59],"trivial":[63],"task":[64],"as":[65,103,178],"it":[66,138],"requires,":[67],"among":[68,124],"others,":[69],"hardware\u2013software":[71],"codesign.":[72],"In":[73],"side,":[76],"most":[77],"high-throughput":[78],"computers":[79],"designed":[81],"aiming":[82],"heterogeneity,":[84],"accelerators":[86],"(e.g.":[87],"Graphics":[88],"Processing":[89],"Units":[90],"(GPUs),":[91],"Field-Programmable":[92],"Gate":[93],"Arrays":[94],"(FPGAs),":[95],"etc.)":[96],"connected":[98],"through":[99],"high-bandwidth":[100],"bus,":[101],"PCI-Express,":[104],"host":[107],"CPUs.":[108],"Applications,":[109],"via":[111],"programmers,":[112],"compilers,":[113],"or":[114],"runtime,":[115],"should":[116],"orchestrate":[117],"data":[118,214],"movement,":[119],"synchronization,":[120],"so":[122],"devices":[125],"different":[127,148],"compute":[128],"memory":[130],"capabilities.":[131],"This":[132,145],"increases":[133],"programming":[135],"complexity":[136],"may":[139],"reduce":[140],"overall":[142],"application":[143],"performance.":[144],"article":[146],"evaluates":[147],"offloading":[149],"strategies":[150],"leverage":[152],"heterogeneous":[153],"systems,":[154],"based":[155],"several":[157,190],"cards":[158],"first-generation":[161],"Xeon":[162],"Phi":[163],"coprocessors":[164],"(Knights":[165],"Corner).":[166],"We":[167],"use":[168],"11-point":[170],"3-D":[171],"Stencil":[172],"kernel":[173],"that":[174,196],"models":[175],"heat":[176],"dissipation":[177],"case":[180],"study.":[181],"Our":[182],"results":[183],"reveal":[184],"substantial":[185],"performance":[186,210],"improvements":[187],"when":[188],"using":[189],"accelerator":[191],"cards.":[192],"Additionally,":[193],"we":[194],"show":[195],"computing":[197],"an":[199],"approximate":[200],"result":[201],"by":[202],"reducing":[203],"communication":[205],"overhead":[206],"can":[207],"yield":[208],"23%":[209],"gains":[211],"double-precision":[213],"sets.":[215]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
