{"id":"https://openalex.org/W1547833503","doi":"https://doi.org/10.1137/070693199","title":"Optimization and Performance Modeling of Stencil Computations on Modern Microprocessors","display_name":"Optimization and Performance Modeling of Stencil Computations on Modern Microprocessors","publication_year":2009,"publication_date":"2009-02-05","ids":{"openalex":"https://openalex.org/W1547833503","doi":"https://doi.org/10.1137/070693199","mag":"1547833503"},"language":"en","primary_location":{"id":"doi:10.1137/070693199","is_oa":false,"landing_page_url":"https://doi.org/10.1137/070693199","pdf_url":null,"source":{"id":"https://openalex.org/S160107561","display_name":"SIAM Review","issn_l":"0036-1445","issn":["0036-1445","1095-7200"],"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 Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digital.library.unt.edu/ark:/67531/metadc933702/m2/1/high_res_d/961524.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104047193","display_name":"Kaushik Datta","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kaushik Datta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shoaib Kamil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shoaib Kamil","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Samuel Williams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Leonid Oliker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leonid Oliker","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"John Shalf","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Shalf","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Katherine Yelick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katherine Yelick","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104047193"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.05555556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"51","issue":"1","first_page":"129","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9975000023841858,"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":0.991100013256073,"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":0.9238294363021851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8376145362854004},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8068150281906128},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7613416910171509},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.5441681742668152},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.49350082874298096},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.48722997307777405},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.4629560112953186},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.46195104718208313},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.4342012107372284},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.43102023005485535},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3213919997215271},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.1925833821296692}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9238294363021851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376145362854004},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8068150281906128},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7613416910171509},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.5441681742668152},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.49350082874298096},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.48722997307777405},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.4629560112953186},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.46195104718208313},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.4342012107372284},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.43102023005485535},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3213919997215271},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.1925833821296692},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":10,"locations":[{"id":"doi:10.1137/070693199","is_oa":false,"landing_page_url":"https://doi.org/10.1137/070693199","pdf_url":null,"source":{"id":"https://openalex.org/S160107561","display_name":"SIAM Review","issn_l":"0036-1445","issn":["0036-1445","1095-7200"],"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 Review","raw_type":"journal-article"},{"id":"pmh:info:ark/67531/metadc933702","is_oa":true,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc933702/","pdf_url":"https://digital.library.unt.edu/ark:/67531/metadc933702/m2/1/high_res_d/961524.pdf","source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal Name: SIAM Review (SIREV) Journal; Journal Volume: 51; Journal Issue: 10; Journal Publication Date: 2009","raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.115.2891","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.115.2891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~kdatta/papers/sirev_stencil.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.179.3010","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.179.3010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.3680","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.3680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~kdatta/pubs/sirev09_stencil.pdf","raw_type":"text"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt2gm4v579","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/2gm4v579","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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"},{"id":"pmh:oai:osti.gov:961524","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/961524","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},{"id":"pmh:qt2gm4v579","is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/2gm4v579","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Datta, Kaushik. (2009). Optimization and Performance Modeling of Stencil Computations on Modern Microprocessors. Lawrence Berkeley National Laboratory. Lawrence Berkeley National Laboratory: Lawrence Berkeley National Laboratory. Retrieved from: http://www.escholarship.org/uc/item/2gm4v579","raw_type":"article"},{"id":"mag:2302356120","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc933702/m2/1/high_res_d/961524.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"mag:1547833503","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/2gm4v579.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S2764971142","display_name":"Lawrence Berkeley National Laboratory","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800592","host_organization_name":"United States Department of Energy","host_organization_lineage":["https://openalex.org/P4320800592"],"host_organization_lineage_names":["United States Department of Energy"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Lawrence Berkeley National Laboratory","raw_type":null}],"best_oa_location":{"id":"pmh:info:ark/67531/metadc933702","is_oa":true,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc933702/","pdf_url":"https://digital.library.unt.edu/ark:/67531/metadc933702/m2/1/high_res_d/961524.pdf","source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal Name: SIAM Review (SIREV) Journal; Journal Volume: 51; Journal Issue: 10; Journal Publication Date: 2009","raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1547833503.pdf","grobid_xml":"https://content.openalex.org/works/W1547833503.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1487278226","https://openalex.org/W2020718546","https://openalex.org/W2109341366","https://openalex.org/W2152914333","https://openalex.org/W4292169137"],"related_works":["https://openalex.org/W2302356120","https://openalex.org/W224992144","https://openalex.org/W2186216222","https://openalex.org/W2148038801","https://openalex.org/W2769005600","https://openalex.org/W2583643880","https://openalex.org/W3080357212","https://openalex.org/W2091545779","https://openalex.org/W2996929894","https://openalex.org/W2129829929","https://openalex.org/W3091752332","https://openalex.org/W1506424797","https://openalex.org/W2560781234","https://openalex.org/W2996597839","https://openalex.org/W2157685422","https://openalex.org/W2977807394","https://openalex.org/W2028067303","https://openalex.org/W2056599241","https://openalex.org/W3092315650","https://openalex.org/W2730450744"],"abstract_inverted_index":{"Stencil-based":[0],"kernels":[1],"constitute":[2],"the":[3,26,39,83,97,102,119,142,163,170,181],"core":[4],"of":[5,20,41,49,101,118,123,144,177,189],"many":[6],"important":[7],"scientific":[8],"applications":[9],"on":[10,46,82,96,167],"block-structured":[11],"grids.":[12],"Unfortunately,":[13],"these":[14],"codes":[15],"achieve":[16],"a":[17,47,105,152,159],"low":[18],"fraction":[19],"peak":[21,179,191],"performance,":[22],"due":[23],"primarily":[24],"to":[25,57,129],"disparity":[27],"between":[28],"processor":[29,185],"and":[30,53,70,88,126],"main":[31],"memory":[32,44,111,137,166],"speeds.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,92],"explore":[38],"impact":[40],"trends":[42,135],"in":[43,136],"subsystems":[45],"variety":[48],"stencil":[50,72,94,124],"optimization":[51],"techniques":[52,81],"develop":[54],"performance":[55,127],"models":[56],"analytically":[58],"guide":[59],"our":[60,114],"optimizations.":[61,147],"Our":[62],"work":[63,115],"targets":[64],"cache":[65],"reuse":[66],"methodologies":[67],"across":[68],"single":[69],"multiple":[71],"sweeps,":[73],"examining":[74],"cache-aware":[75,153],"algorithms":[76],"as":[77,79],"well":[78],"cache-oblivious":[80,160],"Intel":[84],"Itanium2,":[85],"AMD":[86],"Opteron,":[87],"IBM":[89],"Power5.":[90],"Additionally,":[91],"consider":[93],"computations":[95],"heterogeneous":[98],"multicore":[99],"design":[100],"Cell":[103,168,174],"processor,":[104],"machine":[106],"with":[107],"an":[108],"explicitly":[109,164],"managed":[110,165],"hierarchy.":[112],"Overall":[113],"represents":[116],"one":[117],"most":[120],"extensive":[121],"analyses":[122],"optimizations":[125],"modeling":[128],"date.":[130],"Results":[131],"demonstrate":[132],"that":[133,151],"recent":[134],"system":[138],"organization":[139],"have":[140],"reduced":[141],"efficacy":[143],"traditional":[145],"cache-blocking":[146],"We":[148],"also":[149],"show":[150],"implementation":[154],"is":[155],"significantly":[156],"faster":[157],"than":[158],"approach,":[161],"while":[162,180],"enables":[169],"highest":[171],"overall":[172],"efficiency:":[173],"attains":[175],"88%":[176],"algorithmic":[178,190],"best":[182],"competing":[183],"cache-based":[184],"achieves":[186],"only":[187],"54%":[188],"performance.":[192]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
