{"id":"https://openalex.org/W3119652125","doi":"https://doi.org/10.1145/3432261.3436753","title":"SeisSol on Distributed Multi-GPU Systems: CUDA Code Generation for the Modal Discontinuous Galerkin Method","display_name":"SeisSol on Distributed Multi-GPU Systems: CUDA Code Generation for the Modal Discontinuous Galerkin Method","publication_year":2021,"publication_date":"2021-01-14","ids":{"openalex":"https://openalex.org/W3119652125","doi":"https://doi.org/10.1145/3432261.3436753","mag":"3119652125"},"language":"en","primary_location":{"id":"doi:10.1145/3432261.3436753","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3432261.3436753","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3432261.3436753","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3432261.3436753","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025705337","display_name":"Ravil Dorozhinskii","orcid":"https://orcid.org/0000-0003-0397-2166"},"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":"Ravil Dorozhinskii","raw_affiliation_strings":["Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"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":["Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025705337"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.3046,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.75283075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9952999949455261,"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/T11416","display_name":"Numerical methods for differential equations","score":0.9907000064849854,"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/cuda","display_name":"CUDA","score":0.9032304286956787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7994692325592041},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6945485472679138},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5974670648574829},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5768518447875977},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.538899302482605},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5370944738388062},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5122508406639099},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4871370494365692},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4780164957046509},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4536149501800537},{"id":"https://openalex.org/keywords/discontinuous-galerkin-method","display_name":"Discontinuous Galerkin method","score":0.4116392433643341},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.24622756242752075},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.18527182936668396},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.11589190363883972},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10710519552230835},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07896703481674194},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07321342825889587},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07281440496444702}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9032304286956787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994692325592041},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6945485472679138},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5974670648574829},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5768518447875977},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.538899302482605},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5370944738388062},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5122508406639099},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4871370494365692},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4780164957046509},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4536149501800537},{"id":"https://openalex.org/C92244383","wikidata":"https://www.wikidata.org/wiki/Q428273","display_name":"Discontinuous Galerkin method","level":3,"score":0.4116392433643341},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.24622756242752075},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.18527182936668396},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.11589190363883972},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10710519552230835},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07896703481674194},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07321342825889587},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07281440496444702},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3432261.3436753","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3432261.3436753","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3432261.3436753","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1595495","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1595495","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3432261.3436753","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3432261.3436753","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3432261.3436753","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1154770563","display_name":"Centre of Excellence for Exascale in Solid Earth","funder_award_id":"823844","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321047","display_name":"Partnership for Advanced Computing in Europe AISBL","ror":"https://ror.org/038j4hz26"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3119652125.pdf","grobid_xml":"https://content.openalex.org/works/W3119652125.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W78789044","https://openalex.org/W1620888485","https://openalex.org/W1984280619","https://openalex.org/W2000205045","https://openalex.org/W2072800519","https://openalex.org/W2109656481","https://openalex.org/W2119821054","https://openalex.org/W2143131337","https://openalex.org/W2149697434","https://openalex.org/W2284921491","https://openalex.org/W2468576082","https://openalex.org/W2493512717","https://openalex.org/W2519138799","https://openalex.org/W2531293322","https://openalex.org/W2564856016","https://openalex.org/W2612630614","https://openalex.org/W2767668491","https://openalex.org/W2791673912","https://openalex.org/W2914391851","https://openalex.org/W2924040443","https://openalex.org/W2924466044","https://openalex.org/W2942798270","https://openalex.org/W2963137752","https://openalex.org/W2963610942","https://openalex.org/W3095815097","https://openalex.org/W3101543398","https://openalex.org/W3102697874","https://openalex.org/W4285719527","https://openalex.org/W6604447124"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"We":[0,40],"present":[1],"a":[2,15,31],"GPU":[3,48],"implementation":[4],"of":[5],"the":[6,58,68],"high":[7],"order":[8],"Discontinuous":[9],"Galerkin":[10],"(DG)":[11],"scheme":[12,71],"in":[13],"SeisSol,":[14],"software":[16],"package":[17],"for":[18,35,47,57,81],"simulating":[19],"seismic":[20],"waves":[21],"and":[22,72],"earthquake":[23],"dynamics.":[24],"Our":[25],"particular":[26],"focus":[27],"is":[28],"on":[29],"providing":[30],"performance":[32],"portable":[33],"solution":[34],"heterogeneous":[36],"distributed":[37],"multi-GPU":[38],"systems.":[39],"therefore":[41],"redesigned":[42],"SeisSol\u2019s":[43,74],"code":[44,55],"generation":[45,56],"cascade":[46],"programming":[49],"models.":[50],"This":[51],"includes":[52],"CUDA":[53],"source":[54],"performance-critical":[59],"small":[60],"batched":[61],"matrix":[62],"multiplications":[63],"kernels.":[64],"The":[65],"parallelisation":[66],"extends":[67],"existing":[69],"MPI+X":[70],"supports":[73],"cluster-wise":[75],"Local":[76],"Time":[77],"Stepping":[78],"(LTS)":[79],"algorithm":[80],"ADER":[82],"time":[83],"integration.":[84]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}