{"id":"https://openalex.org/W2008005532","doi":"https://doi.org/10.1145/2591006","title":"Algorithm 942","display_name":"Algorithm 942","publication_year":2014,"publication_date":"2014-04-01","ids":{"openalex":"https://openalex.org/W2008005532","doi":"https://doi.org/10.1145/2591006","mag":"2008005532"},"language":"en","primary_location":{"id":"doi:10.1145/2591006","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2591006","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2117/84767","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082199431","display_name":"R. de la Cruz","orcid":"https://orcid.org/0000-0002-2805-3417"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ra\u00fal de la Cruz","raw_affiliation_strings":["Barcelona Supercomputing Center","Barcelona Supercomputing Center,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"raw_affiliation_string":"Barcelona Supercomputing Center,#TAB#","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027534318","display_name":"Mauricio Araya\u2013Polo","orcid":"https://orcid.org/0000-0002-5537-1840"},"institutions":[{"id":"https://openalex.org/I4210090673","display_name":"Comsol (United States)","ror":"https://ror.org/00asd2k77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210090673"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mauricio Araya-Polo","raw_affiliation_strings":["Repsol USA","REPSOL-USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Repsol USA","institution_ids":[]},{"raw_affiliation_string":"REPSOL-USA","institution_ids":["https://openalex.org/I4210090673"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6229,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94508261,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"40","issue":"3","first_page":"1","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9977999925613403,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9959108829498291},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7008464336395264},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.695357620716095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6843109726905823},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6101481318473816},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4859689474105835},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47508659958839417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4375465512275696},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.43751320242881775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23786816000938416}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9959108829498291},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7008464336395264},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.695357620716095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6843109726905823},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6101481318473816},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4859689474105835},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47508659958839417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4375465512275696},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.43751320242881775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23786816000938416},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2591006","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2591006","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/84767","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/84767","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/84767","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/84767","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G471021087","display_name":null,"funder_award_id":"2009501052","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G580227261","display_name":null,"funder_award_id":"RI-211528","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"},{"id":"https://openalex.org/G5837133979","display_name":null,"funder_award_id":"TIN2007-60625","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320321047","display_name":"Partnership for Advanced Computing in Europe AISBL","ror":"https://ror.org/038j4hz26"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W83535271","https://openalex.org/W610778723","https://openalex.org/W994490020","https://openalex.org/W1506943871","https://openalex.org/W1795008753","https://openalex.org/W1825294837","https://openalex.org/W1961751213","https://openalex.org/W1966800152","https://openalex.org/W1967491301","https://openalex.org/W1968013322","https://openalex.org/W1977146182","https://openalex.org/W1991501286","https://openalex.org/W1992419982","https://openalex.org/W1997147891","https://openalex.org/W2002555321","https://openalex.org/W2017445746","https://openalex.org/W2024443647","https://openalex.org/W2034837344","https://openalex.org/W2055253125","https://openalex.org/W2076535184","https://openalex.org/W2078081736","https://openalex.org/W2081422781","https://openalex.org/W2098220211","https://openalex.org/W2108315152","https://openalex.org/W2119042753","https://openalex.org/W2125424217","https://openalex.org/W2127669603","https://openalex.org/W2129471558","https://openalex.org/W2154786353","https://openalex.org/W2295099251","https://openalex.org/W2296760900","https://openalex.org/W2505838289","https://openalex.org/W2953368509","https://openalex.org/W3032177099","https://openalex.org/W3103104567","https://openalex.org/W3202799926","https://openalex.org/W4234960108","https://openalex.org/W4236166769"],"related_works":["https://openalex.org/W3091752332","https://openalex.org/W2177020196","https://openalex.org/W2080076943","https://openalex.org/W4243221193","https://openalex.org/W1561683466","https://openalex.org/W3139770841","https://openalex.org/W104374006","https://openalex.org/W2804126825","https://openalex.org/W2604208239","https://openalex.org/W2315378174"],"abstract_inverted_index":{"Finite":[0],"Difference":[1],"(FD)":[2],"is":[3,72,83,120,310],"a":[4,55,103,175,220,294,311,333,350,373],"widely":[5],"used":[6,264,286],"method":[7,314],"to":[8,121,243,300],"solve":[9],"Partial":[10],"Differential":[11],"Equations":[12],"(PDE).":[13],"PDEs":[14],"are":[15,190,285,327,347],"the":[16,38,44,50,59,65,76,89,94,98,123,127,132,148,152,163,169,172,185,187,199,206,214,217,226,256,290,352,366],"core":[17],"of":[18,54,58,61,97,136,162,177,368],"many":[19],"simulations":[20],"in":[21,74,125,174,219,241,265],"different":[22],"scientific":[23],"fields,":[24],"such":[25],"as":[26,287,355,357],"geophysics,":[27],"astrophysics,":[28],"etc.":[29],"The":[30,114,252,303],"typical":[31],"FD":[32],"solver":[33],"performs":[34],"stencil":[35,51,70,128,173,188,228,296,362],"computations":[36,71,189],"for":[37,293,372],"entire":[39],"computational":[40,133],"domain,":[41,186],"thus":[42],"solving":[43],"differential":[45],"operators.":[46],"In":[47,349],"general":[48],"terms,":[49],"computation":[52,81,129,153,196],"consists":[53],"weighted":[56],"accumulation":[57],"contribution":[60],"neighbor":[62],"points":[63],"along":[64],"cartesian":[66],"axis.":[67],"Therefore,":[68],"optimizing":[69],"crucial":[73],"reducing":[75],"application":[77],"execution":[78],"time.":[79],"Stencil":[80],"performance":[82],"bounded":[84],"by":[85],"two":[86,112,277],"main":[87,115],"factors:":[88],"memory":[90,200,267],"access":[91,201],"pattern":[92,202],"and":[93,141,203,245,261,273,276,281,344],"inefficient":[95],"reuse":[96],"accessed":[99,207],"data.":[100,208],"We":[101],"propose":[102],"novel":[104,308],"algorithm,":[105],"named":[106],"Semi-stencil":[107,149,182,218,257,369],",":[108],"that":[109,306],"tackles":[110],"these":[111],"problems.":[113],"idea":[116],"behind":[117],"this":[118,247,307],"algorithm":[119,150,353],"change":[122],"way":[124],"which":[126,315],"progresses":[130,183],"within":[131],"domain.":[134],"Instead":[135],"accessing":[137],"all":[138,143,324],"required":[139],"neighbors":[140],"adding":[142],"their":[144],"contributions":[145],"at":[146,168],"once,":[147],"divides":[151],"into":[154,319],"several":[155],"updates.":[156],"Then,":[157],"each":[158],"update":[159],"gathers":[160],"half":[161],"axis":[164],"neighbors,":[165],"partially":[166],"computing":[167],"same":[170],"time":[171],"set":[176],"closely":[178],"located":[179],"points.":[180,194],"As":[181],"through":[184],"completed":[191],"on":[192,237,249,339,370],"precomputed":[193],"This":[195],"strategy":[197,258,309],"improves":[198],"efficiently":[204],"reuses":[205],"Our":[209],"initial":[210],"target":[211],"architecture":[212],"was":[213,222],"Cell/B.E.,":[215],"where":[216,289,336],"SPE":[221],"44%":[223],"faster":[224],"than":[225,360],"naive":[227],"implementation.":[229],"Since":[230],"then,":[231],"we":[232,330],"have":[233,331],"continued":[234],"our":[235],"research":[236],"emerging":[238],"multicore":[239,328],"architectures":[240,326],"order":[242],"assess":[244],"extend":[246],"work":[248],"homogeneous":[250],"architectures.":[251,268],"experiments":[253],"presented":[254],"combine":[255],"with":[259],"space-":[260],"time-blocking":[262],"algorithms":[263],"hierarchical":[266],"Two":[269],"x86":[270],"(Intel":[271],"Nehalem":[272],"AMD":[274],"Opteron)":[275],"POWER":[278],"(IBM":[279],"POWER6":[280],"IBM":[282,340],"BG/P)":[283],"platforms":[284],"testbeds,":[288],"best":[291],"improvements":[292],"25-point":[295],"range":[297],"from":[298],"1.27":[299],"1.76\u00d7":[301],"faster.":[302],"results":[304,338],"show":[305],"feasible":[312],"optimization":[313],"may":[316],"be":[317],"integrated":[318],"auto-tuning":[320],"frameworks.":[321],"Also,":[322],"since":[323],"current":[325],"based,":[329],"introduced":[332],"brief":[334],"section":[335],"scalability":[337,367],"POWER7-,":[341],"Intel":[342],"Xeon-,":[343],"MIC-based":[345],"systems":[346],"presented.":[348],"nutshell,":[351],"scales":[354],"well":[356],"or":[358],"better":[359],"other":[361],"techniques.":[363],"For":[364],"instance,":[365],"MIC":[371],"certain":[374],"testcase":[375],"reached":[376],"93.8":[377],"\u00d7":[378],"over":[379],"244":[380],"threads.":[381]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2016-06-24T00:00:00"}
