{"id":"https://openalex.org/W3037462884","doi":"https://doi.org/10.1109/hpec43674.2020.9286237","title":"GPU-Accelerated Discontinuous Galerkin Methods: 30x Speedup on 345 Billion Unknowns","display_name":"GPU-Accelerated Discontinuous Galerkin Methods: 30x Speedup on 345 Billion Unknowns","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3037462884","doi":"https://doi.org/10.1109/hpec43674.2020.9286237","mag":"3037462884"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.15698","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081266095","display_name":"Andrew C. Kirby","orcid":"https://orcid.org/0000-0001-8431-1807"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew C. Kirby","raw_affiliation_strings":["Lincoln Laboratory Supercomputing Center, Massachusetts Institute of Technology, Lexington, MA, USA","Lincoln Laboratory Supercomputing Center, Massachusetts Institute of Technology,Lexington,MA,USA"],"affiliations":[{"raw_affiliation_string":"Lincoln Laboratory Supercomputing Center, Massachusetts Institute of Technology, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Lincoln Laboratory Supercomputing Center, Massachusetts Institute of Technology,Lexington,MA,USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112064657","display_name":"Dimitri J. Mavriplis","orcid":null},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitri J. Mavriplis","raw_affiliation_strings":["Mechanical Engineering, University of Wyoming, Laramie, WY, USA","Mechanical Engineering, University of Wyoming,Laramie,WY,USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, University of Wyoming, Laramie, WY, USA","institution_ids":["https://openalex.org/I12834331"]},{"raw_affiliation_string":"Mechanical Engineering, University of Wyoming,Laramie,WY,USA","institution_ids":["https://openalex.org/I12834331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081266095"],"corresponding_institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.3588,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54533466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9987000226974487,"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":0.9987000226974487,"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/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.9970999956130981,"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/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.911869466304779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7859218120574951},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7445195913314819},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7280118465423584},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6721347570419312},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6184431314468384},{"id":"https://openalex.org/keywords/inviscid-flow","display_name":"Inviscid flow","score":0.5634806752204895},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5247300267219543},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.48003900051116943},{"id":"https://openalex.org/keywords/discontinuous-galerkin-method","display_name":"Discontinuous Galerkin method","score":0.44247275590896606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11516153812408447},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08333581686019897},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07587540149688721}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.911869466304779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859218120574951},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7445195913314819},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7280118465423584},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6721347570419312},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6184431314468384},{"id":"https://openalex.org/C86252789","wikidata":"https://www.wikidata.org/wiki/Q2247765","display_name":"Inviscid flow","level":2,"score":0.5634806752204895},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5247300267219543},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.48003900051116943},{"id":"https://openalex.org/C92244383","wikidata":"https://www.wikidata.org/wiki/Q428273","display_name":"Discontinuous Galerkin method","level":3,"score":0.44247275590896606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11516153812408447},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08333581686019897},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07587540149688721},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.15698","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.15698","pdf_url":"https://arxiv.org/pdf/2006.15698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3037462884","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.15698","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2006.15698","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.15698","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.15698","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.15698","pdf_url":"https://arxiv.org/pdf/2006.15698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3037462884.pdf","grobid_xml":"https://content.openalex.org/works/W3037462884.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W791179977","https://openalex.org/W1528562574","https://openalex.org/W1583515859","https://openalex.org/W1588186680","https://openalex.org/W1651373482","https://openalex.org/W2029541951","https://openalex.org/W2043057066","https://openalex.org/W2086707488","https://openalex.org/W2120919211","https://openalex.org/W2142673658","https://openalex.org/W2148897203","https://openalex.org/W2169631286","https://openalex.org/W2260734724","https://openalex.org/W2284921491","https://openalex.org/W2314831996","https://openalex.org/W2323035077","https://openalex.org/W2324190985","https://openalex.org/W2335597945","https://openalex.org/W2433919184","https://openalex.org/W2466972715","https://openalex.org/W2531293322","https://openalex.org/W2609332365","https://openalex.org/W2614893554","https://openalex.org/W2620663806","https://openalex.org/W2626091712","https://openalex.org/W2782247541","https://openalex.org/W2783989100","https://openalex.org/W2910118867","https://openalex.org/W2910508035","https://openalex.org/W2922340671","https://openalex.org/W2922522393","https://openalex.org/W2962737461","https://openalex.org/W2964086450","https://openalex.org/W2970959587","https://openalex.org/W2972087877","https://openalex.org/W2998486158","https://openalex.org/W3003687283","https://openalex.org/W3099432326","https://openalex.org/W6636831568","https://openalex.org/W6739307100"],"related_works":["https://openalex.org/W3113908379","https://openalex.org/W1585065055","https://openalex.org/W2284921491","https://openalex.org/W2152340913","https://openalex.org/W2166455696","https://openalex.org/W2110874417","https://openalex.org/W2809823315","https://openalex.org/W2964108306","https://openalex.org/W1900162302","https://openalex.org/W2464877849","https://openalex.org/W91434102","https://openalex.org/W2139109319","https://openalex.org/W2148930331","https://openalex.org/W1970773070","https://openalex.org/W2597628894","https://openalex.org/W3129370751","https://openalex.org/W2332025641","https://openalex.org/W2266091017","https://openalex.org/W1863451170","https://openalex.org/W2124730542"],"abstract_inverted_index":{"A":[0,42,80],"discontinuous":[1],"Galerkin":[2],"method":[3],"for":[4,24,73],"the":[5,8,12],"discretization":[6],"of":[7,15,26,82,101],"compressible":[9],"Euler":[10],"equations,":[11],"governing":[13],"equations":[14],"inviscid":[16],"fluid":[17],"dynamics,":[18],"on":[19,38,97],"Cartesian":[20],"meshes":[21],"is":[22,53,65,89],"developed":[23],"use":[25],"Graphical":[27],"Processing":[28],"Units":[29],"via":[30],"OCCA,":[31],"a":[32,74],"unified":[33],"approach":[34],"to":[35,56,68,86],"performance":[36],"portability":[37],"multi-threaded":[39],"hardware":[40],"architectures.":[41],"30x":[43],"time-to-solution":[44],"speedup":[45,96],"over":[46],"CPU-only":[47],"implementations":[48],"using":[49],"non-CUDA-Aware":[50],"MPI":[51,84],"communications":[52],"demonstrated":[54],"up":[55,67],"1,536":[57],"NVIDIA":[58,70,103],"V100":[59,71,104],"GPUs":[60,72],"and":[61],"parallel":[62],"strong":[63],"scalability":[64],"shown":[66],"6,144":[69],"problem":[75],"containing":[76],"345":[77],"billion":[78],"unknowns.":[79],"comparison":[81],"CUDA-Aware":[83],"communication":[85,88],"non-GPUDirect":[87],"performed":[90],"demonstrating":[91],"an":[92],"additional":[93],"24":[94],"%":[95],"eight":[98],"nodes":[99],"composed":[100],"32":[102],"GPUs.":[105]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}