{"id":"https://openalex.org/W4220659857","doi":"https://doi.org/10.1145/3503925","title":"On Memory Traffic and Optimisations for Low-order Finite Element Assembly Algorithms on Multi-core CPUs","display_name":"On Memory Traffic and Optimisations for Low-order Finite Element Assembly Algorithms on Multi-core CPUs","publication_year":2022,"publication_date":"2022-03-04","ids":{"openalex":"https://openalex.org/W4220659857","doi":"https://doi.org/10.1145/3503925"},"language":"en","primary_location":{"id":"doi:10.1145/3503925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503925","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503925","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503925","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003537956","display_name":"James Trotter","orcid":"https://orcid.org/0000-0003-4498-020X"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]},{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"James D. Trotter","raw_affiliation_strings":["Simula Research Laboratory and University of Oslo, Blindern, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-4498-020X","affiliations":[{"raw_affiliation_string":"Simula Research Laboratory and University of Oslo, Blindern, Oslo, Norway","institution_ids":["https://openalex.org/I2799829267","https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084482336","display_name":"Xing Cai","orcid":"https://orcid.org/0000-0003-3706-4414"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]},{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Xing Cai","raw_affiliation_strings":["Simula Research Laboratory and University of Oslo, Blindern, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simula Research Laboratory and University of Oslo, Blindern, Oslo, Norway","institution_ids":["https://openalex.org/I2799829267","https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013806448","display_name":"Simon W. Funke","orcid":"https://orcid.org/0000-0003-4709-8415"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Simon W. Funke","raw_affiliation_strings":["Simula Research Laboratory, Simula Research Laboratory, Lysaker, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simula Research Laboratory, Simula Research Laboratory, Lysaker, Norway","institution_ids":["https://openalex.org/I2799829267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003537956"],"corresponding_institution_ids":["https://openalex.org/I184942183","https://openalex.org/I2799829267"],"apc_list":null,"apc_paid":null,"fwci":0.6994,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6509417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"48","issue":"2","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9984999895095825,"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/T10996","display_name":"Computational Geometry and Mesh Generation","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/computer-science","display_name":"Computer science","score":0.7820298075675964},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6717844009399414},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.622988760471344},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5677175521850586},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5603503584861755},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.5297891497612},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.4975621998310089},{"id":"https://openalex.org/keywords/out-of-core-algorithm","display_name":"Out-of-core algorithm","score":0.47865235805511475},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.39321890473365784},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3203807473182678},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.09963604807853699},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07530730962753296},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07136428356170654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820298075675964},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6717844009399414},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.622988760471344},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5677175521850586},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5603503584861755},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.5297891497612},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.4975621998310089},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.47865235805511475},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.39321890473365784},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3203807473182678},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.09963604807853699},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07530730962753296},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07136428356170654},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503925","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503925","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},{"id":"pmh:oai:www.duo.uio.no:10852/108283","is_oa":true,"landing_page_url":"http://hdl.handle.net/10852/108283","pdf_url":null,"source":{"id":"https://openalex.org/S4306401717","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"0098-3500","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3503925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503925","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503925","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G5244242995","display_name":null,"funder_award_id":"270053","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G697056457","display_name":null,"funder_award_id":"251186","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220659857.pdf","grobid_xml":"https://content.openalex.org/works/W4220659857.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1601728065","https://openalex.org/W1616824231","https://openalex.org/W1946796247","https://openalex.org/W1978064247","https://openalex.org/W1979836673","https://openalex.org/W1987535721","https://openalex.org/W2001088168","https://openalex.org/W2008060144","https://openalex.org/W2018225490","https://openalex.org/W2034197136","https://openalex.org/W2040092451","https://openalex.org/W2052196304","https://openalex.org/W2072132691","https://openalex.org/W2077368913","https://openalex.org/W2091260418","https://openalex.org/W2095420020","https://openalex.org/W2100418324","https://openalex.org/W2100632417","https://openalex.org/W2102076631","https://openalex.org/W2137541800","https://openalex.org/W2139710482","https://openalex.org/W2140741668","https://openalex.org/W2149185537","https://openalex.org/W2149211280","https://openalex.org/W2164925996","https://openalex.org/W2168522485","https://openalex.org/W2169999287","https://openalex.org/W2342281373","https://openalex.org/W2582607288","https://openalex.org/W2612795562","https://openalex.org/W2767520933","https://openalex.org/W2923328826","https://openalex.org/W3011811412","https://openalex.org/W3016268593","https://openalex.org/W3100990548","https://openalex.org/W3104566386","https://openalex.org/W3105886089","https://openalex.org/W3121682852","https://openalex.org/W3122714673","https://openalex.org/W4205634890","https://openalex.org/W4245654886"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W4388257798","https://openalex.org/W3183639206","https://openalex.org/W2044628889","https://openalex.org/W2365659824","https://openalex.org/W2913338224","https://openalex.org/W2624244002"],"abstract_inverted_index":{"Motivated":[0],"by":[1,32],"the":[2,6,19,49,58,61,96,99,112,119,122],"wish":[3],"to":[4,77,95,111],"understand":[5],"achievable":[7],"performance":[8],"of":[9,28,102,121],"finite":[10,134],"element":[11,73,135],"assembly":[12,22,85],"on":[13,48],"unstructured":[14],"computational":[15],"meshes,":[16],"we":[17],"dissect":[18],"standard":[20],"cellwise":[21],"algorithm":[23,86],"into":[24],"four":[25],"kernels,":[26],"two":[27,62],"which":[29],"are":[30,39,105],"dominated":[31],"irregular":[33],"memory":[34,51,103],"traffic.":[35],"Several":[36],"optimisation":[37],"schemes":[38],"studied":[40],"together":[41],"with":[42],"associated":[43],"lower":[44,114],"and":[45,81],"upper":[46],"bounds":[47],"estimated":[50,113],"traffic":[52,104],"volume.":[53],"Apart":[54],"from":[55],"properly":[56],"reordering":[57],"mesh":[59],"entities,":[60],"most":[63],"significant":[64],"optimisations":[65],"include":[66],"adopting":[67],"a":[68,83,127],"lookup":[69],"table":[70],"in":[71,106],"adding":[72],"matrices":[74],"or":[75],"vectors":[76],"their":[78],"global":[79],"counterparts,":[80],"using":[82],"row-wise":[84],"for":[87,129,133],"multi-threaded":[88],"parallelisation.":[89],"Rigorous":[90],"benchmarking":[91],"shows":[92],"that,":[93],"due":[94],"various":[97],"optimisations,":[98,123],"actual":[100],"volumes":[101],"many":[107],"cases":[108],"very":[109],"close":[110],"bounds.":[115],"These":[116],"results":[117],"confirm":[118],"effectiveness":[120],"while":[124],"also":[125],"providing":[126],"recipe":[128],"developing":[130],"efficient":[131],"software":[132],"assembly.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}