{"id":"https://openalex.org/W2913229686","doi":"https://doi.org/10.1109/p3hpc.2018.00010","title":"Heterogeneous CPU-GPU Execution of Stencil Applications","display_name":"Heterogeneous CPU-GPU Execution of Stencil Applications","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2913229686","doi":"https://doi.org/10.1109/p3hpc.2018.00010","mag":"2913229686"},"language":"en","primary_location":{"id":"doi:10.1109/p3hpc.2018.00010","doi":"https://doi.org/10.1109/p3hpc.2018.00010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/p3hpc.2018.00010","pdf_url":null,"source":{"id":"https://openalex.org/S7407105980","display_name":"IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2913229686"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035047284","display_name":"B\u00e1lint Sikl\u00f3si","orcid":"https://orcid.org/0000-0003-1716-5058","observed_orcids":["https://orcid.org/0000-0003-1716-5058"]},"institutions":[{"id":"https://openalex.org/I31882830","display_name":"P\u00e1zm\u00e1ny P\u00e9ter Catholic University","ror":"https://ror.org/05v9kya57","country_code":"HU","type":"education","lineage":["https://openalex.org/I31882830"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Balint Siklosi","raw_affiliation_strings":["Fac. of Inf. Technol. & Bionics, Pazmany Peter Catholic Univ., Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fac. of Inf. Technol. & Bionics, Pazmany Peter Catholic Univ., Budapest, Hungary","institution_ids":["https://openalex.org/I31882830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048478302","display_name":"Istvan Zoltan Reguly","orcid":"https://orcid.org/0000-0002-4385-4204","observed_orcids":["https://orcid.org/0000-0002-4385-4204"]},"institutions":[{"id":"https://openalex.org/I31882830","display_name":"P\u00e1zm\u00e1ny P\u00e9ter Catholic University","ror":"https://ror.org/05v9kya57","country_code":"HU","type":"education","lineage":["https://openalex.org/I31882830"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Istvan Z Reguly","raw_affiliation_strings":["Faculty of Information Technology and Bionics, Pazmany Peter Catholic University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Bionics, Pazmany Peter Catholic University, Budapest, Hungary","institution_ids":["https://openalex.org/I31882830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070789282","display_name":"Gihan R. Mudalige","orcid":"https://orcid.org/0000-0002-1398-5174","observed_orcids":["https://orcid.org/0000-0002-1398-5174"]},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gihan R Mudalige","raw_affiliation_strings":["Department of Computer Science, university of of Warwick, Coventry, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, university of of Warwick, Coventry, United Kingdom","institution_ids":["https://openalex.org/I39555362"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4696,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81469745,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.00019999999494757503,"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":9.999999747378752e-05,"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/performance-portability","display_name":"performance portability","score":0.972000002861023},{"id":"https://openalex.org/keywords/load-balancing","display_name":"load balancing","score":0.8370000123977661},{"id":"https://openalex.org/keywords/polyhedral-analysis","display_name":"polyhedral analysis","score":0.9419999718666077},{"id":"https://openalex.org/keywords/polyhedral-transformations","display_name":"polyhedral transformations","score":0.8730000257492065},{"id":"https://openalex.org/keywords/domain-specific-languages","display_name":"domain-specific languages","score":0.7559999823570251},{"id":"https://openalex.org/keywords/heat-equation","display_name":"heat equation","score":0.8840000033378601},{"id":"https://openalex.org/keywords/gpu-accelerators","display_name":"GPU accelerators","score":0.4860000014305115},{"id":"https://openalex.org/keywords/data-transmission-reduction","display_name":"data transmission reduction","score":0.43299999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8933160305023193},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8713279366493225},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7768563032150269},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6770358085632324},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6690905690193176},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.49498289823532104},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.47197896242141724},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.45727092027664185},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.45123961567878723},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43928030133247375},{"id":"https://openalex.org/C2777138346","wikidata":"https://www.wikidata.org/wiki/Q1714153","display_name":"Performance tuning","level":2,"score":0.42600908875465393},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2945665717124939},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.21558579802513123},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/p3hpc.2018.00010","doi":"https://doi.org/10.1109/p3hpc.2018.00010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/p3hpc.2018.00010","pdf_url":null,"source":{"id":"https://openalex.org/S7407105980","display_name":"IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC)","raw_type":"proceedings-article"},{"id":"pmh:oai:real.mtak.hu:99801","doi":null,"is_oa":false,"landing_page_url":"http://real.mtak.hu/99801/1/Heterogeneous_CPU_GPU_Execution_of_Stencil_Applications.pdf","pdf_url":"http://real.mtak.hu/99801/1/Heterogeneous_CPU_GPU_Execution_of_Stencil_Applications.pdf","source":{"id":"https://openalex.org/S4306400081","display_name":"Repository of the Academy's Library (Library of the Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210140733","host_organization_name":"Library and Information Centre of the Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I4210140733"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W260821384","https://openalex.org/W1577137152","https://openalex.org/W1864199185","https://openalex.org/W1981021420","https://openalex.org/W1988083695","https://openalex.org/W2003798513","https://openalex.org/W2010936531","https://openalex.org/W2015935981","https://openalex.org/W2036551003","https://openalex.org/W2037520749","https://openalex.org/W2039676062","https://openalex.org/W2120723967","https://openalex.org/W2121516352","https://openalex.org/W2121893797","https://openalex.org/W2139116943","https://openalex.org/W2142421493","https://openalex.org/W2159153788","https://openalex.org/W2169711291","https://openalex.org/W2244491995","https://openalex.org/W2311737728","https://openalex.org/W2536891287","https://openalex.org/W2608177516","https://openalex.org/W2743401659","https://openalex.org/W2768814357","https://openalex.org/W3149084271","https://openalex.org/W4248722156","https://openalex.org/W4255162882"],"related_works":["https://openalex.org/W2768814357","https://openalex.org/W2497986104","https://openalex.org/W3207327990","https://openalex.org/W7102555454","https://openalex.org/W2549711633","https://openalex.org/W2916280107","https://openalex.org/W4385765206","https://openalex.org/W4386644650","https://openalex.org/W2903775786","https://openalex.org/W2064735574"],"abstract_inverted_index":{"Heterogeneous":[0],"computer":[1],"architectures":[2],"are":[3,14],"now":[4],"ubiquitous":[5],"in":[6,131],"high":[7,93],"performance":[8,72,175,219],"computing;":[9],"the":[10,54,71,76,107,138,169,208,211],"top":[11],"7":[12],"supercomputers":[13],"all":[15],"built":[16],"with":[17,184],"CPUs":[18,24],"and":[19,25,30,116,129,148,180,188,194],"accelerators.":[20],"Portability":[21],"across":[22,224],"different":[23,103],"GPUs":[26],"is":[27,35],"becoming":[28],"paramount,":[29],"heterogeneous":[31],"scheduling":[32],"of":[33,37,44,58,62,75,102,140,210,227],"computations":[34],"also":[36],"increasing":[38],"interest":[39],"to":[40,95,133,216],"make":[41],"full":[42],"use":[43],"these":[45],"systems.":[46],"In":[47],"this":[48],"paper":[49],"we":[50,120,177],"present":[51],"research":[52],"on":[53,126,137,155,203],"hybrid":[55,195],"CPU-GPU":[56,196],"execution":[57],"an":[59,122],"important":[60],"class":[61],"applications:":[63],"structured":[64],"mesh":[65],"stencil":[66],"codes.":[67],"Our":[68,205],"work":[69],"broadens":[70],"portability":[73,220],"capabilities":[74],"Oxford":[77],"Parallel":[78],"library":[79],"for":[80,99,221],"Structured":[81],"meshes":[82],"(OPS),":[83],"which":[84],"allows":[85],"a":[86,92,100,156,164,200,225],"science":[87],"code":[88],"written":[89],"once":[90],"at":[91],"level":[94,139],"be":[96],"automatically":[97],"parallelised":[98],"range":[101],"architectures.":[104],"We":[105,151,198],"explore":[106],"traditional":[108],"per-loop":[109],"load":[110,135],"balancing":[111,136],"approach":[112],"used":[113],"by":[114],"others,":[115],"highlighting":[117],"its":[118,222],"shortcomings,":[119],"develop":[121],"algorithm":[123],"that":[124],"relies":[125],"polyhedral":[127],"analysis":[128],"transformations":[130],"OPS":[132,212],"allow":[134],"larger":[141],"computational":[142],"stages,":[143],"reducing":[144],"data":[145],"transfer":[146],"requirements":[147],"synchronisation":[149],"points.":[150],"evaluate":[152],"our":[153],"algorithms":[154],"simple":[157],"heat":[158],"equation":[159],"benchmark,":[160],"as":[161,163],"well":[162],"substantially":[165],"more":[166],"complex":[167],"code,":[168],"CloverLeaf":[170],"hydrodynamics":[171],"mini-app.":[172],"To":[173],"demonstrate":[174,199],"portability,":[176],"study":[178],"Intel":[179],"IBM":[181],"systems":[182],"equipped":[183],"NVIDIA":[185],"Kepler,":[186],"Pascal,":[187],"Volta":[189],"GPUs,":[190],"evaluating":[191],"CPU-only,":[192],"GPU-only":[193],"performance.":[197],"1.05-1.2\u00d7":[201],"speedup":[202],"CloverLeaf.":[204],"results":[206],"highlight":[207],"ability":[209],"domain":[213],"specific":[214],"language":[215],"deliver":[217],"effortless":[218],"users":[223],"number":[226],"platforms.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-02-21T00:00:00"}