{"id":"https://openalex.org/W2520660423","doi":"https://doi.org/10.1109/hpcsim.2016.7568426","title":"A cache-aware approach to domain decomposition for stencil-based codes","display_name":"A cache-aware approach to domain decomposition for stencil-based codes","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2520660423","doi":"https://doi.org/10.1109/hpcsim.2016.7568426","mag":"2520660423"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2016.7568426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2016.7568426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101994516","display_name":"Gaurav Saxena","orcid":"https://orcid.org/0000-0001-7667-5053"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gaurav Saxena","raw_affiliation_strings":["School of Computing, University of Leeds, Leeds"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds, Leeds","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050648247","display_name":"Peter K. Jimack","orcid":"https://orcid.org/0000-0001-9463-7595"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter K. Jimack","raw_affiliation_strings":["School of Computing, University of Leeds, Leeds"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds, Leeds","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058883030","display_name":"Mark A. Walkley","orcid":"https://orcid.org/0000-0003-2541-4173"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark A. Walkley","raw_affiliation_strings":["School of Computing, University of Leeds, Leeds"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds, Leeds","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130828816"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"875","last_page":"885"},"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":0.9998000264167786,"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":0.9983000159263611,"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/cache","display_name":"Cache","score":0.8205827474594116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8010700941085815},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7835156917572021},{"id":"https://openalex.org/keywords/domain-decomposition-methods","display_name":"Domain decomposition methods","score":0.7406021952629089},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7268368601799011},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.6766411662101746},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.6417183876037598},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.5657458305358887},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5617170929908752},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5536412596702576},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4978039264678955},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.4389207065105438},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4325729310512543},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.4269486665725708},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4217616021633148},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3907659649848938},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38401031494140625},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3654252886772156},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.28957825899124146},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.18731147050857544},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12975561618804932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0683966875076294}],"concepts":[{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.8205827474594116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010700941085815},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7835156917572021},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.7406021952629089},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7268368601799011},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.6766411662101746},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.6417183876037598},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.5657458305358887},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5617170929908752},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5536412596702576},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4978039264678955},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.4389207065105438},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4325729310512543},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.4269486665725708},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4217616021633148},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3907659649848938},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38401031494140625},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3654252886772156},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.28957825899124146},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.18731147050857544},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12975561618804932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0683966875076294},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpcsim.2016.7568426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2016.7568426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:100732","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W63141727","https://openalex.org/W179546749","https://openalex.org/W1509342228","https://openalex.org/W1510543252","https://openalex.org/W1530872699","https://openalex.org/W1555915743","https://openalex.org/W1564227505","https://openalex.org/W1765408465","https://openalex.org/W1997147891","https://openalex.org/W2002555321","https://openalex.org/W2055253125","https://openalex.org/W2091545779","https://openalex.org/W2095875205","https://openalex.org/W2119042753","https://openalex.org/W2145876975","https://openalex.org/W2148038801","https://openalex.org/W2152914333","https://openalex.org/W2154786353","https://openalex.org/W2499905000","https://openalex.org/W2725179571","https://openalex.org/W3022841918","https://openalex.org/W3121554115","https://openalex.org/W3152199537","https://openalex.org/W4249968602","https://openalex.org/W4302466289","https://openalex.org/W6602555841","https://openalex.org/W6630541929","https://openalex.org/W6630558366","https://openalex.org/W6631554681","https://openalex.org/W6633646031","https://openalex.org/W6670407849","https://openalex.org/W6989454671"],"related_works":["https://openalex.org/W2098406302","https://openalex.org/W2535115842","https://openalex.org/W2734782074","https://openalex.org/W2546991807","https://openalex.org/W2020176098","https://openalex.org/W2076114130","https://openalex.org/W2121191383","https://openalex.org/W1584415117","https://openalex.org/W2500877097","https://openalex.org/W2436169747"],"abstract_inverted_index":{"Partial":[0],"Differential":[1],"Equations":[2],"(PDEs)":[3],"lie":[4],"at":[5,97],"the":[6,25,38,82,98,118,125,153,163,186],"heart":[7],"of":[8,17,27,108,120,168],"numerous":[9],"scientific":[10],"simulations":[11,19],"depicting":[12],"physical":[13],"phenomena.":[14],"The":[15,166],"parallelization":[16],"such":[18,159],"introduces":[20],"additional":[21],"performance":[22,110],"penalties":[23],"in":[24,113,155,203],"form":[26],"local":[28],"and":[29,45,52,63,74,161,191],"global":[30],"synchronization":[31],"among":[32],"cooperating":[33],"processes.":[34],"Domain":[35],"decomposition":[36,84],"partitions":[37],"largest":[39],"shareable":[40],"data":[41],"structures":[42],"into":[43],"sub-domains":[44],"attempts":[46],"to":[47,56,60,105,128,144,178,185,199],"achieve":[48],"perfect":[49],"load":[50],"balance":[51],"minimal":[53],"communication.":[54],"Up":[55],"now":[57],"research":[58],"efforts":[59],"optimize":[61,129],"spatial":[62],"temporal":[64],"cache":[65,95,134],"reuse":[66],"for":[67],"stencil-based":[68],"PDE":[69],"discretizations":[70],"(e.g.":[71],"finite":[72,75],"difference":[73],"element)":[76],"have":[77],"considered":[78],"sub-domain":[79,99],"operations":[80],"after":[81],"domain":[83,111,130,149,201],"has":[85],"been":[86],"determined.":[87],"We":[88,151,189],"derive":[89],"a":[90,102],"cache-oblivious":[91],"heuristic":[92],"that":[93,172,193],"minimizes":[94],"misses":[96,135],"level":[100],"through":[101,158],"quasi-cache-directed":[103],"analysis":[104],"predict":[106],"families":[107],"high":[109],"decompositions":[112,131,160,202],"structured":[114,179],"3-D":[115,180],"grids.":[116],"To":[117],"best":[119],"our":[121,169],"knowledge":[122],"this":[123,204],"is":[124,171,175,195],"first":[126],"work":[127,170],"by":[132],"analyzing":[133],"-":[136],"thus":[137],"connecting":[138],"single":[139],"core":[140],"parameters":[141,147],"(i.e.":[142,148],"cache-misses)":[143],"true":[145],"multicore":[146],"decomposition).":[150],"analyze":[152],"trade-offs":[154],"decreasing":[156],"cache-misses":[157],"increasing":[162],"dynamic":[164],"bandwidth-per-core.":[165],"limitation":[167],"currently,":[173],"it":[174],"applicable":[176],"only":[177],"grids":[181],"with":[182],"cuts":[183],"parallel":[184],"Cartesian":[187],"Axes.":[188],"emphasize":[190],"conclude":[192],"there":[194],"an":[196],"imperative":[197],"need":[198],"re-think":[200],"constantly":[205],"evolving":[206],"multi-core":[207],"era.":[208]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
