{"id":"https://openalex.org/W2055253125","doi":"https://doi.org/10.1145/1111583.1111589","title":"Impact of modern memory subsystems on cache optimizations for stencil computations","display_name":"Impact of modern memory subsystems on cache optimizations for stencil computations","publication_year":2005,"publication_date":"2005-06-12","ids":{"openalex":"https://openalex.org/W2055253125","doi":"https://doi.org/10.1145/1111583.1111589","mag":"2055253125"},"language":"en","primary_location":{"id":"doi:10.1145/1111583.1111589","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1111583.1111589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 workshop on Memory system performance","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/A5039453861","display_name":"Shoaib Kamil","orcid":"https://orcid.org/0000-0001-5965-3717"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shoaib Kamil","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033402901","display_name":"Parry Husbands","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parry Husbands","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113842004","display_name":"Leonid Oliker","orcid":"https://orcid.org/0000-0002-7923-2896"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonid Oliker","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010873686","display_name":"John Shalf","orcid":"https://orcid.org/0000-0002-0608-3690"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Shalf","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091741596","display_name":"Katherine Yelick","orcid":"https://orcid.org/0000-0003-0957-701X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Yelick","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039453861"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":5.0123,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.95304778,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9872000217437744,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9110865592956543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.776192307472229},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7200580835342407},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6774013042449951},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5649509429931641},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.43063247203826904},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.41242730617523193},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.31565749645233154},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.26447394490242004},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1009623110294342}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9110865592956543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.776192307472229},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7200580835342407},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6774013042449951},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5649509429931641},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.43063247203826904},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41242730617523193},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.31565749645233154},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.26447394490242004},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1009623110294342}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1111583.1111589","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1111583.1111589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 workshop on Memory system performance","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.847","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-vis.lbl.gov/Publications/2005/msp2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309411","display_name":"University of California Berkeley","ror":"https://ror.org/01an7q238"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1537879423","https://openalex.org/W1581657066","https://openalex.org/W1967264375","https://openalex.org/W2000018615","https://openalex.org/W2072126248","https://openalex.org/W2076848169","https://openalex.org/W2119042753","https://openalex.org/W2152914333","https://openalex.org/W6631970537"],"related_works":["https://openalex.org/W2147122795","https://openalex.org/W2061075966","https://openalex.org/W3147501184","https://openalex.org/W2167303720","https://openalex.org/W2109715593","https://openalex.org/W3161817247","https://openalex.org/W2012518269","https://openalex.org/W1863436361","https://openalex.org/W2068309140","https://openalex.org/W57688818"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,56,72],"investigate":[4],"the":[5,20,33,63,111,125],"impact":[6],"of":[7,39,65,127],"evolving":[8],"memory":[9,25,69,98,120],"system":[10,121],"features,":[11],"such":[12],"as":[13,82],"large":[14],"on-chip":[15],"caches,":[16],"automatic":[17],"prefetch,":[18],"and":[19,49,78,105],"growing":[21],"distance":[22],"to":[23,46,61],"main":[24],"on":[26,89],"3D":[27],"stencil":[28,87],"computations.":[29],"These":[30],"calculations":[31],"form":[32],"basis":[34],"for":[35,85,101],"a":[36,58,74,83],"wide":[37],"range":[38],"scientific":[40],"applications":[41],"from":[42],"simple":[43,59],"Jacobi":[44],"iterations":[45],"complex":[47],"multigrid":[48],"block":[50],"structured":[51],"adaptive":[52],"PDE":[53],"solvers.":[54],"First":[55],"develop":[57],"benchmark":[60],"evaluate":[62],"effectiveness":[64,108],"prefetching":[66],"in":[67,109],"cache-based":[68],"systems.":[70],"Next":[71],"present":[73],"small":[75],"parameterized":[76],"probe":[77],"validate":[79],"its":[80,107],"use":[81],"proxy":[84],"general":[86],"computations":[88],"three":[90],"modern":[91],"microprocessors.":[92],"We":[93],"then":[94],"derive":[95],"an":[96],"analytical":[97],"cost":[99],"model":[100],"quantifying":[102],"cache-blocking":[103,129],"behavior":[104],"demonstrate":[106,116],"predicting":[110],"stencil-computation":[112],"performance.":[113],"Overall":[114],"results":[115],"that":[117],"recent":[118],"trends":[119],"organization":[122],"have":[123],"reduced":[124],"efficacy":[126],"traditional":[128],"optimizations.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
