{"id":"https://openalex.org/W4413928705","doi":"https://doi.org/10.1145/3765616","title":"Multilevel Interior Penalty Methods on GPUs","display_name":"Multilevel Interior Penalty Methods on GPUs","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4413928705","doi":"https://doi.org/10.1145/3765616"},"language":"en","primary_location":{"id":"doi:10.1145/3765616","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765616","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765616","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":null,"license_id":null,"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":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3765616","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025964696","display_name":"Cu Cui","orcid":"https://orcid.org/0000-0003-0341-4447"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Cu Cui","raw_affiliation_strings":["Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Heidelberg, Germany","Heidelberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074603830","display_name":"Guido Kanschat","orcid":"https://orcid.org/0000-0003-1687-7328"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guido Kanschat","raw_affiliation_strings":["Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Heidelberg, Germany","Heidelberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025964696"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1872835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"51","issue":"3","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9975000023841858,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9973000288009644,"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":0.6621573567390442},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5823678970336914},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5427906513214111},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4479962885379791},{"id":"https://openalex.org/keywords/penalty-method","display_name":"Penalty method","score":0.42883947491645813},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.28814461827278137},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21458739042282104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621573567390442},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5823678970336914},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5427906513214111},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4479962885379791},{"id":"https://openalex.org/C6180225","wikidata":"https://www.wikidata.org/wiki/Q3411771","display_name":"Penalty method","level":2,"score":0.42883947491645813},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28814461827278137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21458739042282104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3765616","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765616","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765616","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3765616","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765616","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765616","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G8659941796","display_name":null,"funder_award_id":"202106380059","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413928705.pdf","grobid_xml":"https://content.openalex.org/works/W4413928705.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1900162302","https://openalex.org/W1979313559","https://openalex.org/W1985144286","https://openalex.org/W2002555321","https://openalex.org/W2018225490","https://openalex.org/W2029725158","https://openalex.org/W2031149877","https://openalex.org/W2033986961","https://openalex.org/W2040651749","https://openalex.org/W2047352485","https://openalex.org/W2055953382","https://openalex.org/W2057630513","https://openalex.org/W2075896209","https://openalex.org/W2076517626","https://openalex.org/W2102076631","https://openalex.org/W2117752372","https://openalex.org/W2120919211","https://openalex.org/W2160635789","https://openalex.org/W2166122567","https://openalex.org/W2225768769","https://openalex.org/W2284921491","https://openalex.org/W2287612569","https://openalex.org/W2571435561","https://openalex.org/W2607476412","https://openalex.org/W2767520933","https://openalex.org/W2943869808","https://openalex.org/W2963610942","https://openalex.org/W2964712419","https://openalex.org/W2981341148","https://openalex.org/W3018086455","https://openalex.org/W3040786754","https://openalex.org/W3099299211","https://openalex.org/W3167826856","https://openalex.org/W3204468590","https://openalex.org/W4231154391","https://openalex.org/W4242960114","https://openalex.org/W4309672181","https://openalex.org/W4386073026","https://openalex.org/W4399664584","https://openalex.org/W4402369978","https://openalex.org/W4408160647","https://openalex.org/W4410424782","https://openalex.org/W4410885890","https://openalex.org/W4411228010"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W3189307731","https://openalex.org/W1428699136","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1998560227"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"matrix-free":[3],"multigrid":[4],"method":[5],"for":[6],"high-order":[7],"Discontinuous":[8],"Galerkin":[9],"(DG)":[10],"finite":[11],"element":[12],"methods":[13],"with":[14,94],"GPU":[15],"acceleration.":[16],"A":[17],"performance":[18,54],"analysis":[19],"is":[20,86],"conducted,":[21],"comparing":[22],"various":[23],"data":[24],"and":[25,34,69,84,91],"compute":[26],"layouts.":[27],"Smoother":[28],"implementations":[29],"are":[30,59],"optimized":[31],"through":[32],"localization":[33],"fast":[35],"diagonalization":[36],"techniques.":[37],"Leveraging":[38],"conflict-free":[39],"access":[40],"patterns":[41],"in":[42,75],"shared":[43],"memory,":[44],"arithmetic":[45],"throughput":[46],"of":[47,51,66,81],"up":[48],"to":[49,96],"40%":[50],"the":[52,64],"peak":[53],"on":[55],"NVIDIA":[56],"A100":[57],"GPUs":[58],"achieved.":[60],"Experimental":[61],"results":[62],"affirm":[63],"effectiveness":[65],"mixed-precision":[67],"approaches":[68],"Message":[70],"Passing":[71],"Interface":[72],"(MPI)":[73],"parallelization":[74],"accelerating":[76],"algorithms.":[77],"Furthermore,":[78],"an":[79],"assessment":[80],"solver":[82],"efficiency":[83],"robustness":[85],"provided":[87],"across":[88],"both":[89],"two":[90],"three":[92],"dimensions,":[93],"applications":[95],"Poisson":[97],"problems.":[98]},"counts_by_year":[],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}