{"id":"https://openalex.org/W1506424797","doi":"https://doi.org/10.1137/140991133","title":"Multicore-Optimized Wavefront Diamond Blocking for Optimizing Stencil Updates","display_name":"Multicore-Optimized Wavefront Diamond Blocking for Optimizing Stencil Updates","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1506424797","doi":"https://doi.org/10.1137/140991133","mag":"1506424797"},"language":"en","primary_location":{"id":"doi:10.1137/140991133","is_oa":false,"landing_page_url":"https://doi.org/10.1137/140991133","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1410.3060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112390928","display_name":"Tareq B. Malas","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"T. Malas","raw_affiliation_strings":["Extreme Computing Research Center (ECRC), King Abdullah University of Science and Tech-nology (KAUST), Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center (ECRC), King Abdullah University of Science and Tech-nology (KAUST), Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"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":"G. Hager","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), Friedrich-Alexander University of Erlangen-Nuremberg, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), Friedrich-Alexander University of Erlangen-Nuremberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017526753","display_name":"Hatem Ltaief","orcid":"https://orcid.org/0000-0002-6897-1095"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"H. Ltaief","raw_affiliation_strings":["Extreme Computing Research Center (ECRC), King Abdullah University of Science and Tech-nology (KAUST), Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center (ECRC), King Abdullah University of Science and Tech-nology (KAUST), Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050502786","display_name":"Holger Stengel","orcid":null},"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":"H. Stengel","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), Friedrich-Alexander University of Erlangen-Nuremberg, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), Friedrich-Alexander University of Erlangen-Nuremberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","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":"G. Wellein","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), Friedrich-Alexander University of Erlangen-Nuremberg, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), Friedrich-Alexander University of Erlangen-Nuremberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021283893","display_name":"David E. Keyes","orcid":"https://orcid.org/0000-0002-4052-7224"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"D. Keyes","raw_affiliation_strings":["Extreme Computing Research Center (ECRC), King Abdullah University of Science and Tech-nology (KAUST), Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center (ECRC), King Abdullah University of Science and Tech-nology (KAUST), Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112390928"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":11.5839,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.98826928,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"37","issue":"4","first_page":"C439","last_page":"C464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7506999969482422,"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":0.7506999969482422,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.052000001072883606,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.045499999076128006,"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/stencil","display_name":"Stencil","score":0.941306471824646},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7633061408996582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7340184450149536},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5447633266448975},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4192701280117035},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4189434349536896},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3335855007171631}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.941306471824646},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7633061408996582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7340184450149536},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5447633266448975},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4192701280117035},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4189434349536896},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3335855007171631}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/140991133","is_oa":false,"landing_page_url":"https://doi.org/10.1137/140991133","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1410.3060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1410.3060","pdf_url":"https://arxiv.org/pdf/1410.3060","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/577336","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/577336","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1410.3060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1410.3060","pdf_url":"https://arxiv.org/pdf/1410.3060","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522241184","https://openalex.org/W1529356657","https://openalex.org/W1908022351","https://openalex.org/W1968013322","https://openalex.org/W1973271197","https://openalex.org/W1973532523","https://openalex.org/W1979457157","https://openalex.org/W1997147891","https://openalex.org/W2002555321","https://openalex.org/W2028798345","https://openalex.org/W2034761517","https://openalex.org/W2039378765","https://openalex.org/W2070961300","https://openalex.org/W2074833026","https://openalex.org/W2096642134","https://openalex.org/W2097757554","https://openalex.org/W2104512032","https://openalex.org/W2115140794","https://openalex.org/W2131218797","https://openalex.org/W2148038801","https://openalex.org/W2150319905","https://openalex.org/W2151764765","https://openalex.org/W2153768689","https://openalex.org/W2160106616","https://openalex.org/W2164890169","https://openalex.org/W2166622045","https://openalex.org/W2205893513","https://openalex.org/W2336353249","https://openalex.org/W2964101311","https://openalex.org/W3106055984","https://openalex.org/W3139770841","https://openalex.org/W3151489216","https://openalex.org/W4235662649","https://openalex.org/W4255560897"],"related_works":["https://openalex.org/W2177020196","https://openalex.org/W2769005600","https://openalex.org/W1429949169","https://openalex.org/W2031026393","https://openalex.org/W2097757554","https://openalex.org/W2039378765","https://openalex.org/W2185562986","https://openalex.org/W3139770841","https://openalex.org/W3091752332","https://openalex.org/W2056599241"],"abstract_inverted_index":{"The":[0,90],"importance":[1],"of":[2,29,46,65,110],"stencil-based":[3],"algorithms":[4],"in":[5,83,96],"computational":[6],"science":[7],"has":[8],"focused":[9],"attention":[10],"on":[11,140],"optimized":[12],"parallel":[13],"implementations":[14],"for":[15],"multilevel":[16],"cache-based":[17],"processors.":[18],"Temporal":[19],"blocking":[20,69],"schemes":[21,78,92],"leverage":[22],"the":[23,44,54,63,103,127,130,134],"large":[24,81],"bandwidth":[25],"and":[26,35,70,123,133],"low":[27],"latency":[28],"caches":[30],"to":[31,73,87],"accelerate":[32],"stencil":[33,76],"updates":[34],"approach":[36],"theoretical":[37],"peak":[38],"performance.":[39],"A":[40],"key":[41],"ingredient":[42],"is":[43],"reduction":[45],"data":[47,51],"traffic":[48],"across":[49],"slow":[50],"paths,":[52],"especially":[53],"main":[55],"memory":[56,84,124,131],"interface.":[57],"In":[58],"this":[59],"work":[60],"we":[61],"combine":[62],"ideas":[64],"multicore":[66],"wavefront":[67],"temporal":[68],"diamond":[71],"tiling":[72],"arrive":[74],"at":[75],"update":[77,108],"that":[79],"show":[80,93],"reductions":[82],"pressure":[85,128],"compared":[86],"existing":[88],"approaches.":[89],"resulting":[91],"performance":[94,138],"advantages":[95],"bandwidth-starved":[97],"situations,":[98],"which":[99],"are":[100],"exacerbated":[101],"by":[102],"high":[104],"bytes":[105],"per":[106],"lattice":[107],"case":[109],"variable":[111],"coefficients.":[112],"Our":[113],"thread":[114],"groups":[115],"concept":[116],"provides":[117],"a":[118,141],"controllable":[119],"trade-off":[120],"between":[121,129],"concurrency":[122],"usage,":[125],"shifting":[126],"interface":[132],"CPU.":[135],"We":[136],"present":[137],"results":[139],"contemporary":[142],"Intel":[143],"processor.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":4}],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}