{"id":"https://openalex.org/W1616173761","doi":"https://doi.org/10.1142/s0129626410000296","title":"LEVERAGING SHARED CACHES FOR PARALLEL TEMPORAL BLOCKING OF STENCIL CODES ON MULTICORE PROCESSORS AND CLUSTERS","display_name":"LEVERAGING SHARED CACHES FOR PARALLEL TEMPORAL BLOCKING OF STENCIL CODES ON MULTICORE PROCESSORS AND CLUSTERS","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W1616173761","doi":"https://doi.org/10.1142/s0129626410000296","mag":"1616173761"},"language":"en","primary_location":{"id":"doi:10.1142/s0129626410000296","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626410000296","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1006.3148","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003949750","display_name":"Markus Wittmann","orcid":"https://orcid.org/0000-0002-4812-9052"},"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":"MARKUS WITTMANN","raw_affiliation_strings":["Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"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":["Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039308392","display_name":"Jan Treibig","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":"JAN TREIBIG","raw_affiliation_strings":["Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"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":["Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08184143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"04","first_page":"359","last_page":"376"},"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":0.9995999932289124,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9990000128746033,"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":0.8486666083335876},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7344129681587219},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6943554878234863},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6820507049560547},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.6312100887298584},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5426576137542725},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5262676477432251},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4894532263278961},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46298494935035706},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.44686007499694824},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.44509774446487427},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.41574063897132874},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36566126346588135},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35312163829803467},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.1069512665271759},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09721976518630981},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07738476991653442}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486666083335876},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7344129681587219},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6943554878234863},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6820507049560547},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.6312100887298584},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5426576137542725},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5262676477432251},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4894532263278961},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46298494935035706},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.44686007499694824},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.44509774446487427},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.41574063897132874},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36566126346588135},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35312163829803467},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.1069512665271759},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09721976518630981},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07738476991653442},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1142/s0129626410000296","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626410000296","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"},{"id":"pmh:oai:arXiv.org:1006.3148","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1006.3148","pdf_url":"https://arxiv.org/pdf/1006.3148","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":null,"raw_type":"text"},{"id":"mag:1616173761","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1006.3148.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1006.3148","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1006.3148","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1006.3148","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1006.3148","pdf_url":"https://arxiv.org/pdf/1006.3148","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1616173761.pdf","grobid_xml":"https://content.openalex.org/works/W1616173761.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1997147891"],"related_works":["https://openalex.org/W2559303350","https://openalex.org/W1985130351","https://openalex.org/W2185482126","https://openalex.org/W1978219354","https://openalex.org/W2962978274","https://openalex.org/W2957583380","https://openalex.org/W2247651031","https://openalex.org/W2029866183","https://openalex.org/W2496213259","https://openalex.org/W2243920665","https://openalex.org/W2306912361","https://openalex.org/W2513448415","https://openalex.org/W2002932832","https://openalex.org/W2336580963","https://openalex.org/W2904604538","https://openalex.org/W1616582327","https://openalex.org/W3089469538","https://openalex.org/W2133637307","https://openalex.org/W2059659334","https://openalex.org/W1964389544"],"abstract_inverted_index":{"Bandwidth-starved":[0],"multicore":[1,43],"chips":[2],"have":[3],"become":[4],"ubiquitous.":[5],"It":[6],"is":[7],"well":[8],"known":[9],"that":[10,35,62,82,105],"the":[11,23,26],"performance":[12,85],"of":[13,39,92],"stencil":[14],"codes":[15],"can":[16,108],"be":[17,109],"improved":[18],"by":[19],"temporal":[20,106],"blocking,":[21],"lessening":[22],"pressure":[24],"on":[25,67],"memory":[27,75],"interface.":[28],"We":[29,79],"introduce":[30],"a":[31,96,113],"new":[32],"pipelined":[33],"approach":[34],"makes":[36],"explicit":[37],"use":[38],"shared":[40,71],"caches":[41,72],"in":[42,112],"environments":[44],"and":[45,48,73,94],"minimizes":[46],"synchronization":[47],"boundary":[49],"overhead.":[50],"Benchmark":[51],"results":[52],"are":[53,87],"presented":[54],"for":[55,89],"three":[56],"current":[57],"x86-based":[58],"microprocessors,":[59],"showing":[60],"clearly":[61],"our":[63],"optimization":[64],"works":[65],"best":[66],"designs":[68],"with":[69,118],"high-speed":[70],"low":[74],"bandwidth":[76],"per":[77],"core.":[78],"furthermore":[80],"demonstrate":[81],"simple":[83],"bandwidth-based":[84],"models":[86],"inaccurate":[88],"this":[90],"kind":[91],"algorithm":[93],"employ":[95],"more":[97],"elaborate,":[98],"synthetic":[99],"modeling":[100],"procedure.":[101],"Finally":[102],"we":[103],"show":[104],"blocking":[107],"employed":[110],"successfully":[111],"hybrid":[114],"shared/distributed-memory":[115],"environment,":[116],"albeit":[117],"limited":[119],"benefit":[120],"at":[121],"strong":[122],"scaling.":[123]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
