{"id":"https://openalex.org/W2128544095","doi":"https://doi.org/10.1142/s0129626414410047","title":"Domain-Specific Optimization of Two Jacobi Smoother Kernels and Their Evaluation in the ECM Performance Model","display_name":"Domain-Specific Optimization of Two Jacobi Smoother Kernels and Their Evaluation in the ECM Performance Model","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2128544095","doi":"https://doi.org/10.1142/s0129626414410047","mag":"2128544095"},"language":"en","primary_location":{"id":"doi:10.1142/s0129626414410047","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626414410047","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","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/A5005047392","display_name":"Stefan Kronawitter","orcid":"https://orcid.org/0000-0003-1893-0508"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Stefan Kronawitter","raw_affiliation_strings":["Department of Informatics and Mathematics, University of Passau, Innstra\u00dfe 33, 94032 Passau, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics and Mathematics, University of Passau, Innstra\u00dfe 33, 94032 Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050502786","display_name":"Holger Stengel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Holger Stengel","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), Martensstra\u00dfe 1, 91058 Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), Martensstra\u00dfe 1, 91058 Erlangen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), Martensstra\u00dfe 1, 91058 Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), Martensstra\u00dfe 1, 91058 Erlangen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001151726","display_name":"Christian Lengauer","orcid":"https://orcid.org/0000-0002-2717-3417"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Lengauer","raw_affiliation_strings":["Department of Informatics and Mathematics, University of Passau, Innstra\u00dfe 33, 94032 Passau, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics and Mathematics, University of Passau, Innstra\u00dfe 33, 94032 Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005047392"],"corresponding_institution_ids":["https://openalex.org/I186354981"],"apc_list":null,"apc_paid":null,"fwci":0.9194,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76494589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"24","issue":"03","first_page":"1441004","last_page":"1441004"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9957000017166138,"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/stencil","display_name":"Stencil","score":0.9848742485046387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8144585490226746},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7626221179962158},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5818502902984619},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5308341383934021},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5167149901390076},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5055620670318604},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.43788641691207886},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4215864837169647},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.420148104429245},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.2119053602218628},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.19319835305213928},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16309183835983276},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15085816383361816},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.104607492685318},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.08805683255195618}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9848742485046387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144585490226746},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7626221179962158},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5818502902984619},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5308341383934021},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5167149901390076},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5055620670318604},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.43788641691207886},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4215864837169647},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.420148104429245},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.2119053602218628},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.19319835305213928},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16309183835983276},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15085816383361816},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.104607492685318},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.08805683255195618},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0129626414410047","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626414410047","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","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":20,"referenced_works":["https://openalex.org/W76123042","https://openalex.org/W576226109","https://openalex.org/W1480947737","https://openalex.org/W1491178396","https://openalex.org/W1522241184","https://openalex.org/W1650934639","https://openalex.org/W1968013322","https://openalex.org/W1997147891","https://openalex.org/W2002555321","https://openalex.org/W2003798513","https://openalex.org/W2039378765","https://openalex.org/W2096642134","https://openalex.org/W2135682468","https://openalex.org/W2148038801","https://openalex.org/W2150319905","https://openalex.org/W2154786353","https://openalex.org/W2160106616","https://openalex.org/W2554304410","https://openalex.org/W2964101311","https://openalex.org/W3099022356"],"related_works":["https://openalex.org/W2769005600","https://openalex.org/W2097757554","https://openalex.org/W2039378765","https://openalex.org/W2185562986","https://openalex.org/W2056599241","https://openalex.org/W3091752332","https://openalex.org/W2889543163","https://openalex.org/W2753769741","https://openalex.org/W2977807394","https://openalex.org/W2912790413"],"abstract_inverted_index":{"Our":[0],"aim":[1],"is":[2],"to":[3,7,12,40,63,114],"apply":[4,115],"program":[5],"transformations":[6,39,117],"stencil":[8,27,49,106],"codes":[9,107],"in":[10,26,34,126],"order":[11],"yield":[13],"the":[14,60,67,87,93,96],"highest":[15],"possible":[16],"performance.":[17,29],"We":[18,30,72,84,119],"recognize":[19],"memory":[20],"bandwidth":[21],"as":[22],"a":[23,32,124],"major":[24],"limitation":[25],"code":[28,101],"conducted":[31],"study":[33],"which":[35],"we":[36],"applied":[37],"optimizing":[38],"two":[41,78,81],"Jacobi":[42],"smoother":[43],"kernels:":[44],"one":[45,51],"3D":[46,52],"1st-order":[47],"7-point":[48],"and":[50,80,108],"3rd-order":[53],"19-point":[54],"stencil.":[55],"To":[56],"obtain":[57],"high":[58],"performance,":[59],"optimizations":[61,91],"have":[62],"be":[64,112],"customized":[65],"for":[66,89],"execution":[68,109],"platform":[69],"at":[70],"hand.":[71],"illustrate":[73],"this":[74],"by":[75],"experiments":[76],"on":[77],"consumer":[79],"server":[82],"architectures.":[83],"also":[85],"verified":[86],"need":[88],"complex":[90],"with":[92,103],"help":[94],"of":[95],"Execution-Cache-Memory":[97],"performance":[98],"model.":[99],"A":[100],"generator":[102,125],"knowledge":[104],"about":[105],"platforms":[110],"should":[111],"able":[113],"our":[116],"automatically.":[118],"are":[120],"working":[121],"towards":[122],"such":[123],"project":[127],"ExaStencils.":[128]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
