{"id":"https://openalex.org/W2008436719","doi":"https://doi.org/10.1137/130935781","title":"Modeling the Performance of Geometric Multigrid Stencils on Multicore Computer Architectures","display_name":"Modeling the Performance of Geometric Multigrid Stencils on Multicore Computer Architectures","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2008436719","doi":"https://doi.org/10.1137/130935781","mag":"2008436719"},"language":"en","primary_location":{"id":"doi:10.1137/130935781","is_oa":false,"landing_page_url":"https://doi.org/10.1137/130935781","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"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 Journal on Scientific Computing","raw_type":"journal-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/A5043775275","display_name":"Pieter Ghysels","orcid":"https://orcid.org/0000-0002-5981-5234"},"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"]},{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE","US"],"is_corresponding":false,"raw_author_name":"Pieter Ghysels","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720","Department of Mathematics and Computer Science, University of Antwerp, Middelheimlaan 1, B-2020 Antwerp, Belgium,","Intel ExaScience Lab, Kapeldreef 75, B-3001 Leuven, Belgium, and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Antwerp, Middelheimlaan 1, B-2020 Antwerp, Belgium,","institution_ids":["https://openalex.org/I149213910"]},{"raw_affiliation_string":"Intel ExaScience Lab, Kapeldreef 75, B-3001 Leuven, Belgium, and","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064358152","display_name":"Wim Vanroose","orcid":"https://orcid.org/0000-0001-8349-1391"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wim Vanroose","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Antwerp, Middelheimlaan 1, B-2020 Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Antwerp, Middelheimlaan 1, B-2020 Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6238,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92789292,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"37","issue":"2","first_page":"C194","last_page":"C216"},"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":0.9926999807357788,"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":0.9914000034332275,"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":0.7708001136779785},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6650499105453491},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.6606247425079346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.649872899055481},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.6181098222732544},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5135812759399414},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.497299462556839},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.49160346388816833},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4830189645290375},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.46385714411735535},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4359845519065857},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3768351972103119},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.35027337074279785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28577160835266113},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1526869833469391},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.12674695253372192}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7708001136779785},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6650499105453491},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.6606247425079346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.649872899055481},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.6181098222732544},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5135812759399414},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.497299462556839},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.49160346388816833},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4830189645290375},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.46385714411735535},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4359845519065857},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3768351972103119},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35027337074279785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28577160835266113},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1526869833469391},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.12674695253372192},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/130935781","is_oa":false,"landing_page_url":"https://doi.org/10.1137/130935781","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"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 Journal on Scientific Computing","raw_type":"journal-article"},{"id":"pmh:c:irua:124484","is_oa":false,"landing_page_url":"https://hdl.handle.net/10067/1244840151162165141","pdf_url":null,"source":{"id":"https://openalex.org/S4377196495","display_name":"Anet (University of Antwerp)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149213910","host_organization_name":"University of Antwerp","host_organization_lineage":["https://openalex.org/I149213910"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W136905915","https://openalex.org/W1506342804","https://openalex.org/W1515448847","https://openalex.org/W1522241184","https://openalex.org/W1530872699","https://openalex.org/W1560263223","https://openalex.org/W1575701986","https://openalex.org/W1604759439","https://openalex.org/W1650934639","https://openalex.org/W1774469134","https://openalex.org/W1825532946","https://openalex.org/W1907157228","https://openalex.org/W1964639877","https://openalex.org/W1979457157","https://openalex.org/W1997147891","https://openalex.org/W2002555321","https://openalex.org/W2006962349","https://openalex.org/W2025093669","https://openalex.org/W2034761517","https://openalex.org/W2048955023","https://openalex.org/W2064744742","https://openalex.org/W2070961300","https://openalex.org/W2072763916","https://openalex.org/W2077143534","https://openalex.org/W2087479145","https://openalex.org/W2088949989","https://openalex.org/W2104512032","https://openalex.org/W2128249697","https://openalex.org/W2131413854","https://openalex.org/W2133248904","https://openalex.org/W2145194992","https://openalex.org/W2150319905","https://openalex.org/W2165439482","https://openalex.org/W2298668594","https://openalex.org/W2407443438","https://openalex.org/W3099022356","https://openalex.org/W3138143451","https://openalex.org/W4234740575"],"related_works":["https://openalex.org/W2014327818","https://openalex.org/W1409194387","https://openalex.org/W61888946","https://openalex.org/W2269110805","https://openalex.org/W3105739589","https://openalex.org/W2896552114","https://openalex.org/W2105221648","https://openalex.org/W2097757554","https://openalex.org/W2560894929","https://openalex.org/W4378805959"],"abstract_inverted_index":{"The":[0,212],"basic":[1],"building":[2],"blocks":[3],"of":[4,15,44,51,59,76,146],"the":[5,45,52,57,66,73,77,80,87,101,109,134,140,154,163,186,218],"classic":[6],"geometric":[7],"multigrid":[8,135],"algorithm":[9],"all":[10],"have":[11],"a":[12,41,91,96,116,130,151],"low":[13],"ratio":[14],"executed":[16],"floating":[17,48],"point":[18,49],"operations":[19],"per":[20,68],"byte":[21,69],"fetched":[22],"from":[23],"memory.":[24],"On":[25],"modern":[26],"computer":[27],"architectures,":[28],"such":[29],"computational":[30],"kernels":[31],"are":[32],"typically":[33],"bound":[34],"by":[35,178],"memory":[36],"traffic":[37],"and":[38,162,195,203],"achieve":[39],"only":[40],"small":[42],"percentage":[43],"theoretical":[46,219],"peak":[47],"performance":[50,131,172,214],"underlying":[53],"hardware.":[54],"We":[55,189],"suggest":[56],"use":[58],"state-of-the-art":[60],"(stencil)":[61],"compiler":[62],"techniques":[63],"to":[64,115,158,176,182],"improve":[65],"flop":[67],"ratio,":[70],"also":[71],"called":[72],"arithmetic":[74,119,183],"intensity,":[75],"steps":[78],"in":[79,108],"algorithm.":[81],"Our":[82,171],"focus":[83],"will":[84],"be":[85,112],"on":[86,100,139,199,207],"smoother":[88,110],"which":[89],"is":[90,150,215],"repeated":[92],"stencil":[93],"application.":[94],"With":[95],"tiling":[97],"approach":[98],"based":[99,138],"polyhedral":[102],"loop":[103],"optimization":[104],"framework,":[105],"data":[106,160],"reuse":[107,161],"can":[111],"improved,":[113],"leading":[114],"higher":[117],"effective":[118],"intensity.":[120],"For":[121,143],"an":[122],"academic":[123],"constant":[124],"coefficient":[125],"Poisson":[126],"problem,":[127],"we":[128],"present":[129],"model":[132,173],"for":[133,167,192,204],"$V$-cycle":[136],"solver":[137],"tiled":[141],"smoother.":[142],"increasing":[144],"numbers":[145],"smoothing":[147,169],"steps,":[148],"there":[149],"trade-off":[152],"between":[153],"improved":[155],"efficiency":[156],"due":[157],"better":[159],"additional":[164],"flops":[165],"required":[166],"extra":[168],"steps.":[170],"predicts":[174],"time":[175],"solution":[177],"linking":[179],"convergence":[180],"rate":[181],"intensity":[184],"via":[185],"roofline":[187],"model.":[188],"show":[190],"results":[191],"two-dimensional":[193],"(2D)":[194],"three-dimensional":[196],"(3D)":[197],"simulations":[198,206],"Intel":[200,208],"Sandy":[201],"Bridge":[202],"2D":[205],"Xeon":[209],"Phi":[210],"architectures.":[211],"actual":[213],"compared":[216],"with":[217],"predictions.":[220]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
