{"id":"https://openalex.org/W2899133120","doi":"https://doi.org/10.1109/hpcs.2018.00073","title":"Vectorization of Riemann solvers for the single- and multi-layer Shallow Water Equations","display_name":"Vectorization of Riemann solvers for the single- and multi-layer Shallow Water Equations","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2899133120","doi":"https://doi.org/10.1109/hpcs.2018.00073","mag":"2899133120"},"language":"en","primary_location":{"id":"doi:10.1109/hpcs.2018.00073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs.2018.00073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1506348","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022439820","display_name":"Chaulio R. Ferreira","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Chaulio R. Ferreira","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006551640","display_name":"Kyle T. Mandli","orcid":"https://orcid.org/0000-0002-8267-5989"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle T. Mandli","raw_affiliation_strings":["Applied Physics and Applied Mathematics Department, Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"Applied Physics and Applied Mathematics Department, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039371456","display_name":"Michael B\u00e4der","orcid":"https://orcid.org/0000-0003-4780-4164"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Bader","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022439820"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.2488,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77940222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"75","issue":null,"first_page":"415","last_page":"422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11416","display_name":"Numerical methods for differential equations","score":0.9757999777793884,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.8439491987228394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8126622438430786},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7282048463821411},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7226694226264954},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6177315711975098},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5629955530166626},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.554359495639801},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.45840930938720703},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.43225765228271484},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3897291123867035},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2615275979042053}],"concepts":[{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.8439491987228394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126622438430786},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7282048463821411},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7226694226264954},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6177315711975098},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5629955530166626},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.554359495639801},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.45840930938720703},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43225765228271484},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3897291123867035},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2615275979042053}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpcs.2018.00073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs.2018.00073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1506348","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1506348","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1506348","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1506348","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"","raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/6","display_name":"Clean water and sanitation","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G1193710487","display_name":null,"funder_award_id":"NYSTAR","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G120275728","display_name":null,"funder_award_id":"Univer","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G1782817616","display_name":null,"funder_award_id":"G20RR030893","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2925894945","display_name":"Multi-Scale Computational Methods for Coastal Flooding","funder_award_id":"1720288","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3054523606","display_name":null,"funder_award_id":"234439/2014-9","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G3601516360","display_name":null,"funder_award_id":"Brazil","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G4048685953","display_name":null,"funder_award_id":"1G20RR030893-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5079005330","display_name":null,"funder_award_id":"support","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"},{"id":"https://openalex.org/F4320335380","display_name":"Graduate School, Technische Universit\u00e4t M\u00fcnchen","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W83535271","https://openalex.org/W348433680","https://openalex.org/W1521146888","https://openalex.org/W1555627060","https://openalex.org/W1980292254","https://openalex.org/W2004686369","https://openalex.org/W2034368364","https://openalex.org/W2050445534","https://openalex.org/W2063517087","https://openalex.org/W2106839265","https://openalex.org/W2124799255","https://openalex.org/W2131592052","https://openalex.org/W2495959456","https://openalex.org/W2682544458","https://openalex.org/W2773818793","https://openalex.org/W2793673377","https://openalex.org/W4293397848","https://openalex.org/W6746398149","https://openalex.org/W6749912582"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W1908180445","https://openalex.org/W2127324789","https://openalex.org/W2120385681","https://openalex.org/W2035419609","https://openalex.org/W3024308452","https://openalex.org/W2056079253","https://openalex.org/W4244894488","https://openalex.org/W2022113063","https://openalex.org/W1939907483"],"abstract_inverted_index":{"We":[0,70,153],"discuss":[1],"vectorization":[2],"of":[3,41,74,82,89,105,135,169],"normal":[4],"and":[5,12,21,118,143],"transverse":[6],"Riemann":[7,77],"solvers":[8,78],"for":[9,87,162],"the":[10,30,38,42,45,72,75,80,113,140,148,163,167,170],"single-":[11],"multi-layer":[13],"shallow":[14],"water":[15],"equations.":[16],"Our":[17,96],"approach":[18],"is":[19,25],"simple":[20],"portable,":[22],"as":[23],"it":[24],"based":[26],"on":[27,139,147],"auto-vectorization":[28],"by":[29,33,166],"compiler,":[31],"aided":[32],"OpenMP":[34],"4.0":[35],"directives.":[36],"Despite":[37],"high":[39],"complexity":[40],"solver":[43],"routines,":[44],"Intel":[46,120],"Fortran":[47],"Compiler":[48],"proved":[49],"itself":[50],"able":[51],"to":[52,58,137,145,178],"successfully":[53],"vectorize":[54],"loops":[55],"containing":[56],"calls":[57],"these":[59,157],"solvers,":[60],"after":[61],"only":[62],"a":[63,84,108],"few":[64],"small":[65],"changes":[66],"in":[67],"their":[68],"code.":[69],"evaluate":[71],"performance":[73,97,133],"vectorized":[76],"within":[79],"context":[81],"GeoClaw,":[83],"software":[85],"designed":[86],"simulation":[88,171],"geophysical":[90],"flows":[91],"with":[92,102,112,125],"finite":[93],"volume":[94],"methods.":[95],"studies":[98],"consider":[99],"two":[100],"platforms":[101],"different":[103],"sets":[104],"SIMD":[106],"instructions:":[107],"dual-socket":[109],"Haswell":[110],"system":[111],"AVX2":[114],"instruction":[115],"set":[116],"(256-bit)":[117],"an":[119],"Xeon":[121],"Phi":[122],"(Knights":[123],"Landing)":[124],"AVX-512":[126],"instructions":[127],"(512-bit).":[128],"The":[129],"experimental":[130],"results":[131],"indicate":[132],"improvements":[134],"up":[136,144],"2.1x":[138],"former":[141],"platform":[142],"6.5x":[146],"latter":[149],"(with":[150],"double-precision":[151],"arithmetic).":[152],"also":[154],"show":[155],"that":[156],"speedups":[158],"can":[159],"easily":[160],"compensate":[161],"overhead":[164],"introduced":[165],"rearrangement":[168],"data":[172],"structures,":[173],"which":[174],"might":[175],"be":[176],"necessary":[177],"achieve":[179],"efficient":[180],"vectorization.":[181]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
