{"id":"https://openalex.org/W1980140364","doi":"https://doi.org/10.1145/2688500.2688517","title":"Scalable and efficient implementation of 3d unstructured meshes computation: a case study on matrix assembly","display_name":"Scalable and efficient implementation of 3d unstructured meshes computation: a case study on matrix assembly","publication_year":2015,"publication_date":"2015-01-24","ids":{"openalex":"https://openalex.org/W1980140364","doi":"https://doi.org/10.1145/2688500.2688517","mag":"1980140364"},"language":"en","primary_location":{"id":"doi:10.1145/2688500.2688517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2688500.2688517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5059759642","display_name":"Lo\u00efc Th\u00e9bault","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165330","display_name":"Institut Lavoisier de Versailles","ror":"https://ror.org/05mzd8v39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4210128300","https://openalex.org/I4210165330"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Lo\u00efc Th\u00e9bault","raw_affiliation_strings":["University of Versailles, France"],"affiliations":[{"raw_affiliation_string":"University of Versailles, France","institution_ids":["https://openalex.org/I4210165330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027015251","display_name":"Eric Petit","orcid":"https://orcid.org/0000-0001-5047-1407"},"institutions":[{"id":"https://openalex.org/I4210165330","display_name":"Institut Lavoisier de Versailles","ror":"https://ror.org/05mzd8v39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4210128300","https://openalex.org/I4210165330"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Eric Petit","raw_affiliation_strings":["University of Versailles, France"],"affiliations":[{"raw_affiliation_string":"University of Versailles, France","institution_ids":["https://openalex.org/I4210165330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113434373","display_name":"Quang Dinh","orcid":null},"institutions":[{"id":"https://openalex.org/I1307600426","display_name":"Dassault Aviation (France)","ror":"https://ror.org/02as1sh25","country_code":"FR","type":"company","lineage":["https://openalex.org/I1307600426"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Quang Dinh","raw_affiliation_strings":["Dassault Aviation, France","Dassault Aviation, , France"],"affiliations":[{"raw_affiliation_string":"Dassault Aviation, France","institution_ids":["https://openalex.org/I1307600426"]},{"raw_affiliation_string":"Dassault Aviation, , France","institution_ids":["https://openalex.org/I1307600426"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059759642"],"corresponding_institution_ids":["https://openalex.org/I4210165330"],"apc_list":null,"apc_paid":null,"fwci":3.6272,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9275475,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"129"},"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":0.9994999766349792,"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":0.9925000071525574,"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":0.8829853534698486},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.8136274218559265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7784053087234497},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7378149032592773},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.5549628138542175},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.543242871761322},{"id":"https://openalex.org/keywords/domain-decomposition-methods","display_name":"Domain decomposition methods","score":0.4848884046077728},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46077650785446167},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4288754463195801},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.42007771134376526},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41405802965164185},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41363397240638733},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.41099244356155396},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.31149065494537354},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.2953583002090454},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2042347490787506},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.11002802848815918}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8829853534698486},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.8136274218559265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784053087234497},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7378149032592773},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.5549628138542175},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.543242871761322},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.4848884046077728},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46077650785446167},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4288754463195801},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.42007771134376526},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41405802965164185},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41363397240638733},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.41099244356155396},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.31149065494537354},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2953583002090454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2042347490787506},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.11002802848815918},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2688500.2688517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2688500.2688517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4138220520","display_name":null,"funder_award_id":"610741","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1510543252","https://openalex.org/W1522731666","https://openalex.org/W1946796247","https://openalex.org/W1971343078","https://openalex.org/W1980322368","https://openalex.org/W1980562919","https://openalex.org/W1990808267","https://openalex.org/W1991173503","https://openalex.org/W1997196200","https://openalex.org/W2009196736","https://openalex.org/W2017198538","https://openalex.org/W2028918287","https://openalex.org/W2072725684","https://openalex.org/W2077368913","https://openalex.org/W2095420020","https://openalex.org/W2101863832","https://openalex.org/W2124480634","https://openalex.org/W2153904572","https://openalex.org/W2154118576","https://openalex.org/W2163027735","https://openalex.org/W2163842512","https://openalex.org/W2170230845","https://openalex.org/W2398115286","https://openalex.org/W2436525433","https://openalex.org/W2499905000","https://openalex.org/W2997945685","https://openalex.org/W4251549117","https://openalex.org/W6654740601","https://openalex.org/W7025263956"],"related_works":["https://openalex.org/W2739740241","https://openalex.org/W1974923383","https://openalex.org/W2085105049","https://openalex.org/W2475524688","https://openalex.org/W2522739246","https://openalex.org/W2148563915","https://openalex.org/W2526069705","https://openalex.org/W1998641004","https://openalex.org/W2024016913","https://openalex.org/W2269110805"],"abstract_inverted_index":{"Exposing":[0],"massive":[1],"parallelism":[2,64],"on":[3,20,94,141,162,195,201,211],"3D":[4],"unstructured":[5],"meshes":[6],"computation":[7],"with":[8,29,38,144,150,167],"efficient":[9],"load":[10],"balancing":[11],"and":[12,23,65,68,88,118,191,215],"minimal":[13],"synchronizations":[14],"is":[15],"challenging.":[16],"Current":[17],"approaches":[18],"relying":[19],"domain":[21,51,116],"decomposition":[22,52,117],"mesh":[24,69,120],"coloring":[25,70],"struggle":[26],"to":[27,53,60,74,115,119,183,218],"scale":[28],"the":[30,95,145,174,196,212],"increasing":[31],"number":[32],"of":[33,100],"cores":[34,164,190,214],"per":[35,171],"nodes,":[36],"especially":[37],"new":[39,80],"many-core":[40],"processors.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"an":[47,101,135,157],"hybrid":[48],"approach":[49,93,114],"using":[50],"exploit":[54,61,75],"distributed":[55],"memory":[56,63,86],"parallelism,":[57],"Divide-and-Conquer,":[58],"D&C,":[59],"shared":[62],"improve":[66],"locality,":[67,87],"at":[71],"core":[72],"level":[73],"vectors.":[76],"It":[77,139],"illustrates":[78],"a":[79,124,128,151,180],"trade-off":[81],"for":[82],"many-cores":[83],"between":[84],"structuredness,":[85],"vectorization.":[89],"We":[90,110],"evaluate":[91],"our":[92,112],"finite":[96],"element":[97],"matrix":[98],"assembly":[99],"industrial":[102],"fluid":[103],"dynamic":[104],"code":[105],"developed":[106],"by":[107],"Dassault":[108],"Aviation.":[109],"compare":[111],"D&C":[113,122,155,207],"coloring.":[121],"achieves":[123],"high":[125],"parallel":[126,193],"efficiency,":[127],"good":[129],"data":[130],"locality":[131],"as":[132,134],"well":[133],"improved":[136],"bandwidth":[137],"usage.":[138],"competes":[140],"current":[142],"nodes":[143],"optimized":[146],"pure":[147],"MPI":[148],"version":[149,178],"minimum":[152],"10%":[153],"speed-up.":[154],"shows":[156],"impressive":[158],"319x":[159],"strong":[160],"scaling":[161],"512":[163],"(32":[165],"nodes)":[166],"only":[168],"2000":[169],"vertices":[170],"core.":[172],"Finally,":[173],"Intel":[175,185,220],"Xeon":[176,187,203,222],"Phi":[177,204],"has":[179,208],"performance":[181,216],"similar":[182,217],"10":[184],"E5-2665":[186,221],"Sandy":[188,223],"Bridge":[189,224],"95%":[192],"efficiency":[194,210],"60":[197],"physical":[198,213],"cores.":[199,225],"Running":[200],"4":[202],"(240":[205],"cores),":[206],"92%":[209],"33":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}