{"id":"https://openalex.org/W3138973966","doi":"https://doi.org/10.1109/cgo51591.2021.9370316","title":"YaskSite: Stencil Optimization Techniques Applied to Explicit ODE Methods on Modern Architectures","display_name":"YaskSite: Stencil Optimization Techniques Applied to Explicit ODE Methods on Modern Architectures","publication_year":2021,"publication_date":"2021-02-27","ids":{"openalex":"https://openalex.org/W3138973966","doi":"https://doi.org/10.1109/cgo51591.2021.9370316","mag":"3138973966"},"language":"en","primary_location":{"id":"doi:10.1109/cgo51591.2021.9370316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo51591.2021.9370316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5058357790","display_name":"Christie Louis Alappat","orcid":"https://orcid.org/0000-0003-4548-8727"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christie L. Alappat","raw_affiliation_strings":["University of Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077145003","display_name":"Johannes Seiferth","orcid":null},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Seiferth","raw_affiliation_strings":["University of Bayreuth, Bayreuth, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bayreuth, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["University of Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036300591","display_name":"Matthias Korch","orcid":"https://orcid.org/0000-0001-7267-0378"},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Korch","raw_affiliation_strings":["University of Bayreuth, Bayreuth, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bayreuth, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080647016","display_name":"Thomas Rauber","orcid":"https://orcid.org/0000-0002-3102-6858"},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Rauber","raw_affiliation_strings":["University of Bayreuth, Bayreuth, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bayreuth, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["University of Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058357790"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.4606,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56263806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"186"},"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":0.9993000030517578,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8309316039085388},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.805125892162323},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.581336259841919},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5813117027282715},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.580871045589447},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5505285263061523},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5192444324493408},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5143888592720032},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4887564182281494},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4165727198123932},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.23514437675476074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309316039085388},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.805125892162323},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.581336259841919},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5813117027282715},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.580871045589447},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5505285263061523},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5192444324493408},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5143888592720032},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4887564182281494},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4165727198123932},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.23514437675476074},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cgo51591.2021.9370316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo51591.2021.9370316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},{"id":"pmh:oai:eref.uni-bayreuth.de:70579","is_oa":false,"landing_page_url":"https://eref.uni-bayreuth.de/70579/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196442","display_name":"ERef Bayreuth (University of Bayreuth)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I54009628","host_organization_name":"University of Bayreuth","host_organization_lineage":["https://openalex.org/I54009628"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Aufsatz in einem Buch"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6116119245","display_name":null,"funder_award_id":"01IH16012A,01IH16012C","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W35088483","https://openalex.org/W1506424797","https://openalex.org/W1964031104","https://openalex.org/W1972209410","https://openalex.org/W2002555321","https://openalex.org/W2034761517","https://openalex.org/W2035701183","https://openalex.org/W2078636996","https://openalex.org/W2104512032","https://openalex.org/W2119042753","https://openalex.org/W2124931755","https://openalex.org/W2140707050","https://openalex.org/W2150319905","https://openalex.org/W2155580296","https://openalex.org/W2173545083","https://openalex.org/W2561650451","https://openalex.org/W2588108287","https://openalex.org/W2791258966","https://openalex.org/W2791494644","https://openalex.org/W2805254823","https://openalex.org/W2891241286","https://openalex.org/W2898099374","https://openalex.org/W2909602723","https://openalex.org/W2933196433","https://openalex.org/W2950444855","https://openalex.org/W2951815798","https://openalex.org/W2957142384","https://openalex.org/W2962978274","https://openalex.org/W3005380678","https://openalex.org/W3016197610","https://openalex.org/W3020936970","https://openalex.org/W3037770788","https://openalex.org/W3038517668","https://openalex.org/W3045469217","https://openalex.org/W3099448935","https://openalex.org/W3100119968","https://openalex.org/W3100998497","https://openalex.org/W3101625228","https://openalex.org/W3103041597","https://openalex.org/W3104900731","https://openalex.org/W3106055984","https://openalex.org/W3122375428","https://openalex.org/W3151489216","https://openalex.org/W4232301837","https://openalex.org/W4243796884","https://openalex.org/W4249968602","https://openalex.org/W6751941297","https://openalex.org/W6781611969","https://openalex.org/W6785715140"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2008005532","https://openalex.org/W1971603802","https://openalex.org/W1977185554","https://openalex.org/W2336044659","https://openalex.org/W4391382578"],"abstract_inverted_index":{"The":[0],"landscape":[1],"of":[2,48],"multi-core":[3],"architectures":[4,71],"is":[5,56],"growing":[6],"more":[7],"complex":[8],"and":[9,21,36,133,142,154,163],"diverse.":[10],"Optimal":[11],"application":[12,113],"performance":[13,75,81,138,147],"tuning":[14,102],"parameters":[15,82],"can":[16,31,97],"vary":[17],"widely":[18],"across":[19],"CPUs,":[20],"finding":[22],"them":[23],"in":[24],"a":[25,45],"possibly":[26],"multidimensional":[27],"parameter":[28],"search":[29],"space":[30],"be":[32,98],"time":[33,153],"consuming,":[34],"expensive":[35],"potentially":[37],"infeasible.":[38],"In":[39],"this":[40],"work,":[41],"we":[42,92,119],"introduce":[43],"YaskSite,":[44],"tool":[46],"capable":[47],"tackling":[49],"these":[50],"challenges":[51],"for":[52,111,127],"stencil":[53],"computations.":[54],"YaskSite":[55,121],"built":[57],"upon":[58],"Intel's":[59],"YASK":[60],"framework.":[61],"It":[62],"combines":[63],"YASK's":[64],"flexibility":[65],"to":[66,87,104,145],"deal":[67],"with":[68,72],"different":[69],"target":[70],"the":[73,85,89,107,112,136,158],"Execution-Cache-Memory":[74],"model,":[76],"which":[77],"enables":[78],"identifying":[79],"optimal":[80],"analytically":[83],"without":[84],"need":[86],"run":[88],"code.":[90],"Further":[91],"show":[93,134],"that":[94,135],"YaskSite's":[95],"features":[96],"exploited":[99],"by":[100],"external":[101],"frameworks":[103],"reliably":[105],"select":[106],"most":[108],"efficient":[109],"kernel(s)":[110],"at":[114,149],"hand.":[115],"To":[116],"demonstrate":[117],"this,":[118],"integrate":[120],"into":[122],"Offsite,":[123],"an":[124],"offline":[125],"tuner":[126],"explicit":[128],"ordinary":[129],"differential":[130],"equation":[131],"methods,":[132],"generated":[137],"predictions":[139],"are":[140],"reliable":[141],"accurate,":[143],"leading":[144],"considerable":[146],"gains":[148],"minimal":[150],"code":[151],"generation":[152],"autotuning":[155],"costs":[156],"on":[157],"latest":[159],"Intel":[160],"Cascade":[161],"Lake":[162],"AMD":[164],"Rome":[165],"CPUs.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
