{"id":"https://openalex.org/W2129471558","doi":"https://doi.org/10.1145/1178597.1178605","title":"Implicit and explicit optimizations for stencil computations","display_name":"Implicit and explicit optimizations for stencil computations","publication_year":2006,"publication_date":"2006-10-22","ids":{"openalex":"https://openalex.org/W2129471558","doi":"https://doi.org/10.1145/1178597.1178605","mag":"2129471558"},"language":"en","primary_location":{"id":"doi:10.1145/1178597.1178605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1178597.1178605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 workshop on Memory system performance and correctness","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/uc/item/4zc8s8z0","any_repository_has_fulltext":true},"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","Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062194228","display_name":"Ashim K. Datta","orcid":"https://orcid.org/0000-0002-1397-6892"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Datta","raw_affiliation_strings":["University of California, Berkeley, CA","Univ. of California, Berkeley, CA (United States)"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Univ. of California, Berkeley, CA (United States)","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":["University of California, Berkeley, CA","Univ. of California, Berkeley, CA (United States)"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Univ. of California, Berkeley, CA (United States)","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023338930","display_name":"Lenny Oliker","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":"Leonid Oliker","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA","Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)","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","Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112630097","display_name":"Katherine Yelick","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"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 and University of California, Berkeley, CA","Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)","Univ. of California, Berkeley, CA (United States)"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA and University of California, Berkeley, CA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I95457486"]},{"raw_affiliation_string":"Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Univ. of California, Berkeley, CA (United States)","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5039453861"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":9.093,"has_fulltext":true,"cited_by_count":131,"citation_normalized_percentile":{"value":0.98533306,"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":"51","last_page":"60"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.998199999332428,"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":0.9980999827384949,"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/parallel-computing","display_name":"Parallel computing","score":0.8483401536941528},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.8475724458694458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8409889936447144},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7004623413085938},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.6742006540298462},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.6381689310073853},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.6380965113639832},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5380055904388428},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.509107768535614},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.5076848268508911},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.4934788942337036},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.48556777834892273},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.4568397104740143},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4208257496356964},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.15814220905303955}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8483401536941528},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8475724458694458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409889936447144},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7004623413085938},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.6742006540298462},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.6381689310073853},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.6380965113639832},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5380055904388428},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.509107768535614},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.5076848268508911},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4934788942337036},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.48556777834892273},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.4568397104740143},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4208257496356964},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.15814220905303955}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1145/1178597.1178605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1178597.1178605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 workshop on Memory system performance and correctness","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt4zc8s8z0","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/4zc8s8z0","pdf_url":"https://escholarship.org/uc/item/4zc8s8z0","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":"Proceedings of the 2006 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness Mspc 2006","raw_type":"article"},{"id":"pmh:oai:osti.gov:1407050","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1407050","pdf_url":"https://www.osti.gov/servlets/purl/1407050","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:ark:/13030/qt4zc8s8z0","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.122.2783","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.122.2783","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/~samw/research/papers/mspc06.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.5171","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.5171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bebop.cs.berkeley.edu/pubs/stencil-mspc06.pdf","raw_type":"text"},{"id":"pmh:qt4zc8s8z0","is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/4zc8s8z0","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":"Kamil, S; Datta, K; Williams, S; Oliker, L; Shalf, J; & Yelick, K. (2006). Implicit and explicit optimizations for stencil computations. Proceedings of the 2006 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness, MSPC 2006, 51 - 60. doi: 10.1145/1178597.1178605. Lawrence Berkeley National Laboratory: Lawrence Berkeley National Laboratory. Retrieved from: http://www.escholarship.org/uc/item/4zc8s8z0","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt4zc8s8z0","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/4zc8s8z0","pdf_url":"https://escholarship.org/uc/item/4zc8s8z0","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":"Proceedings of the 2006 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness Mspc 2006","raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5199999809265137,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2129471558.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1600567712","https://openalex.org/W1827355354","https://openalex.org/W1968347730","https://openalex.org/W1975059575","https://openalex.org/W2052196304","https://openalex.org/W2055253125","https://openalex.org/W2103817093","https://openalex.org/W2109859355","https://openalex.org/W2152914333","https://openalex.org/W2160106616","https://openalex.org/W4292169137","https://openalex.org/W4382891143"],"related_works":["https://openalex.org/W2098406302","https://openalex.org/W2535115842","https://openalex.org/W1584415117","https://openalex.org/W1998391448","https://openalex.org/W2121191383","https://openalex.org/W2076114130","https://openalex.org/W2546991807","https://openalex.org/W2020176098","https://openalex.org/W2734782074","https://openalex.org/W2538519144"],"abstract_inverted_index":{"Stencil-based":[0],"kernels":[1],"constitute":[2],"the":[3,25,39,45,54,59,84,100,120,131],"core":[4],"of":[5,19,44,58],"many":[6],"scientific":[7],"applications":[8],"on":[9,37,92,124],"block-structured":[10],"grids.":[11],"Unfortunately,":[12],"these":[13],"codes":[14],"achieve":[15],"a":[16,78,93,107,114],"low":[17],"fraction":[18],"peak":[20],"performance,":[21],"due":[22],"primarily":[23],"to":[24,82,130],"disparity":[26],"between":[27],"processor":[28],"and":[29,49,77,118,140],"main":[30],"memory":[31,42,98,123,138],"speeds.":[32],"We":[33],"examine":[34],"several":[35],"optimizations":[36,63],"both":[38,71],"conventional":[40],"cache-based":[41],"systems":[43],"Itanium":[46],"2,":[47],"Opteron,":[48],"Power5,":[50,132],"as":[51,53],"well":[52],"heterogeneous":[55],"multicore":[56],"design":[57],"Cell":[60,101,125],"processor.":[61,102],"The":[62],"target":[64],"cache":[65,74,85,115],"reuse":[66],"across":[67],"stencil":[68,90],"sweeps,":[69],"including":[70],"an":[72,96],"implicit":[73],"oblivious":[75,116],"approach":[76,109,117],"cache-aware":[79,108],"algorithm":[80],"blocked":[81],"match":[83],"structure.":[86],"Finally,":[87],"we":[88],"consider":[89],"computations":[91],"machine":[94],"with":[95],"explicitly-managed":[97],"hierarchy,":[99],"Overall,":[103],"results":[104],"show":[105],"that":[106,119],"is":[110,126,141],"significantly":[111],"faster":[112],"than":[113],"explicitly":[121],"managed":[122],"more":[127,137],"efficient:":[128],"Relative":[129],"it":[133],"has":[134],"almost":[135],"2x":[136],"bandwidth":[139],"3.7x":[142],"faster.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}