{"id":"https://openalex.org/W4382315185","doi":"https://doi.org/10.1007/978-3-031-32041-5_4","title":"Efficient GPU Offloading with\u00a0OpenMP for\u00a0a\u00a0Hyperbolic Finite Volume Solver on\u00a0Dynamically Adaptive Meshes","display_name":"Efficient GPU Offloading with\u00a0OpenMP for\u00a0a\u00a0Hyperbolic Finite Volume Solver on\u00a0Dynamically Adaptive Meshes","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4382315185","doi":"https://doi.org/10.1007/978-3-031-32041-5_4"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-32041-5_4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-32041-5_4","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-32041-5_4.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-32041-5_4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074090215","display_name":"Mario Wille","orcid":"https://orcid.org/0000-0003-2567-643X"},"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":"Mario Wille","raw_affiliation_strings":["TUM School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"TUM School of Computation, Information and Technology, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075309768","display_name":"Tobias Weinzierl","orcid":"https://orcid.org/0000-0002-6208-1841"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tobias Weinzierl","raw_affiliation_strings":["Department of Computer Science, Institute for Data Science\u2014Large-scale Computing, Durham University, Durham, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Institute for Data Science\u2014Large-scale Computing, Durham University, Durham, UK","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058346268","display_name":"Gonzalo Brito Gadeschi","orcid":"https://orcid.org/0000-0003-1138-3679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gonzalo Brito Gadeschi","raw_affiliation_strings":["NVIDIA, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Munich, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052150558","display_name":"Michael J. Bader","orcid":"https://orcid.org/0009-0000-4334-1938"},"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":["TUM School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"TUM School of Computation, Information and Technology, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074090215"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.4995,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91523713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9962000250816345,"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":0.9962000250816345,"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/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.989300012588501,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9822999835014343,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8975777626037598},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7719558477401733},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6046535968780518},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5712210536003113},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.4861280918121338},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4294436275959015},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4193827509880066},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.41074472665786743},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22430971264839172},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.17608627676963806},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.11378780007362366},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07796275615692139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8975777626037598},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7719558477401733},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6046535968780518},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5712210536003113},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.4861280918121338},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4294436275959015},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4193827509880066},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.41074472665786743},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22430971264839172},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.17608627676963806},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.11378780007362366},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07796275615692139},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-031-32041-5_4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-32041-5_4","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-32041-5_4.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:dro.dur.ac.uk.OAI2:38678","is_oa":true,"landing_page_url":"http://dro.dur.ac.uk/38678/","pdf_url":"https://durham-repository.worktribe.com/preview/1134356/38678.pdf","source":{"id":"https://openalex.org/S4377196258","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bhatele,  A. &amp; Hammond,  J. &amp; Baboulin,  M. &amp; Kruse,  C.  (Eds.).  High Performance Computing. ISC High Performance 2023. : Springer, pp. 65-85, Lecture Notes in Computer Science, Vol.13948","raw_type":"Book chapter"},{"id":"pmh:oai:durham-repository.worktribe.com:1134318","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/1134318","pdf_url":"https://durham-repository.worktribe.com/file/1134318/1/Published%20Conference%20Proceeding","source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1715404","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1715404","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":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-32041-5_4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-32041-5_4","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-32041-5_4.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4115941747","display_name":null,"funder_award_id":"Ministry of Education","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G41932317","display_name":null,"funder_award_id":"W026775","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4443409137","display_name":"An ExCALIBUR Multigrid Solver Toolbox for ExaHyPE","funder_award_id":"EP/X019497/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5554892693","display_name":null,"funder_award_id":"EP/W026775","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7672679674","display_name":"Particles At eXascale on High Performance Computers (PAX-HPC)","funder_award_id":"EP/W026775/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320664","display_name":"Durham University","ror":"https://ror.org/01v29qb04"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4382315185.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W981517633","https://openalex.org/W1543935889","https://openalex.org/W2008084436","https://openalex.org/W2028723587","https://openalex.org/W2141801163","https://openalex.org/W2508004730","https://openalex.org/W2745436534","https://openalex.org/W2798536650","https://openalex.org/W2808938949","https://openalex.org/W2886210973","https://openalex.org/W2905532857","https://openalex.org/W2946545004","https://openalex.org/W2949666040","https://openalex.org/W2970036919","https://openalex.org/W3124694492","https://openalex.org/W3167401864","https://openalex.org/W3203920625","https://openalex.org/W3204436950","https://openalex.org/W3214100902","https://openalex.org/W4221061044","https://openalex.org/W4221162886","https://openalex.org/W4285134078","https://openalex.org/W4321636701"],"related_works":["https://openalex.org/W2349791858","https://openalex.org/W1578381328","https://openalex.org/W2368611950","https://openalex.org/W254684032","https://openalex.org/W1824582190","https://openalex.org/W2149344539","https://openalex.org/W1848192231","https://openalex.org/W2388026393","https://openalex.org/W120214571","https://openalex.org/W4291801887"],"abstract_inverted_index":{"Abstract":[0],"We":[1,129],"identify":[2],"and":[3,36,77,87,119,146],"show":[4,51,130],"how":[5],"to":[6,41,46,57,61,93,123,139],"overcome":[7,140],"an":[8,158],"OpenMP":[9],"bottleneck":[10,145],"in":[11],"the":[12,47,58,65,75,95,100,108,124,141,149],"administration":[13,136],"of":[14,39,44,116,151,160],"GPU":[15,59,66,142],"memory.":[16],"It":[17],"arises":[18],"for":[19,110],"a":[20],"wave":[21],"equation":[22],"solver":[23],"on":[24,99,107],"dynamically":[25],"adaptive":[26],"block-structured":[27],"Cartesian":[28],"meshes,":[29],"which":[30],"keeps":[31,114],"all":[32,38,111],"CPU":[33,112],"threads":[34,126],"busy":[35],"allows":[37],"them":[40],"offload":[42],"sets":[43],"patches":[45],"GPU.":[48],"Our":[49],"studies":[50],"that":[52,131],"multithreaded,":[53],"concurrent,":[54],"non-deterministic":[55],"access":[56],"leads":[60],"performance":[62],"breakdowns,":[63],"since":[64],"memory":[67,96,106,118,135,143],"bookkeeping":[68,144],"as":[69],"offered":[70],"through":[71],"OpenMP\u2019s":[72],"clause,":[73],"i.e.,":[74],"allocation":[76],"freeing,":[78],"becomes":[79],"another":[80],"runtime":[81],"challenge":[82],"besides":[83],"expensive":[84],"data":[85],"transfer":[86],"actual":[88],"computation.":[89],"We,":[90],"therefore,":[91],"propose":[92],"retain":[94],"management":[97],"responsibility":[98],"host:":[101],"A":[102],"caching":[103],"mechanism":[104],"acquires":[105],"accelerator":[109],"threads,":[113],"hold":[115],"this":[117,132],"hands":[120],"it":[121],"out":[122],"offloading":[125],"upon":[127],"demand.":[128],"user-managed,":[133],"CPU-based":[134],"helps":[137],"us":[138],"speeds":[147],"up":[148],"time-to-solution":[150],"Finite":[152],"Volume":[153],"kernels":[154],"by":[155],"more":[156],"than":[157],"order":[159],"magnitude.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
