{"id":"https://openalex.org/W2098972669","doi":"https://doi.org/10.1142/s0129626414410059","title":"High-Level Programming of Stencil Computations on Multi-GPU Systems Using the SkelCL Library","display_name":"High-Level Programming of Stencil Computations on Multi-GPU Systems Using the SkelCL Library","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2098972669","doi":"https://doi.org/10.1142/s0129626414410059","mag":"2098972669"},"language":"en","primary_location":{"id":"doi:10.1142/s0129626414410059","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626414410059","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"},"type":"article","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/A5016319844","display_name":"Michel Steuwer","orcid":"https://orcid.org/0000-0001-5048-0741"},"institutions":[{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michel Steuwer","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany","Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany","institution_ids":["https://openalex.org/I22465464"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany#TAB#","institution_ids":["https://openalex.org/I22465464"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017380426","display_name":"Michael Haidl","orcid":"https://orcid.org/0000-0003-0225-498X"},"institutions":[{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Haidl","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany","Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany","institution_ids":["https://openalex.org/I22465464"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany#TAB#","institution_ids":["https://openalex.org/I22465464"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005173073","display_name":"Stefan Breuer","orcid":null},"institutions":[{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Breuer","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany","Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany","institution_ids":["https://openalex.org/I22465464"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany#TAB#","institution_ids":["https://openalex.org/I22465464"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061421539","display_name":"Sergei Gorlatch","orcid":"https://orcid.org/0000-0003-3857-9380"},"institutions":[{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sergei Gorlatch","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany","Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany","institution_ids":["https://openalex.org/I22465464"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Muenster, Muenster, Germany#TAB#","institution_ids":["https://openalex.org/I22465464"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22465464"],"apc_list":null,"apc_paid":null,"fwci":1.8482,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85893941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":"03","first_page":"1441005","last_page":"1441005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10591","display_name":"Theoretical and Computational Physics","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter Physics"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955999851226807,"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/stencil","display_name":"Stencil","score":0.9900616407394409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8562902808189392},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.778775691986084},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7608702182769775},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6150467395782471},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5492536425590515},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4154466986656189},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.40040379762649536},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19389978051185608},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09439927339553833}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9900616407394409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8562902808189392},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.778775691986084},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7608702182769775},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6150467395782471},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5492536425590515},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4154466986656189},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40040379762649536},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19389978051185608},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09439927339553833},{"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:10.1142/s0129626414410059","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626414410059","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:eprints.gla.ac.uk:148974","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":false,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Articles"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W182526625","https://openalex.org/W1545533962","https://openalex.org/W1965067012","https://openalex.org/W2001258868","https://openalex.org/W2016450267","https://openalex.org/W2025437939","https://openalex.org/W2048007254","https://openalex.org/W2051439100","https://openalex.org/W2069963734","https://openalex.org/W2099491351","https://openalex.org/W2104512032","https://openalex.org/W2124265561","https://openalex.org/W2142063750","https://openalex.org/W2151788546","https://openalex.org/W2271183134","https://openalex.org/W2519454815","https://openalex.org/W4229035505"],"related_works":["https://openalex.org/W2177020196","https://openalex.org/W1618681060","https://openalex.org/W3189307731","https://openalex.org/W2167527468","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227","https://openalex.org/W1429949169","https://openalex.org/W2586370661"],"abstract_inverted_index":{"The":[0],"implementation":[1],"of":[2,30,131],"stencil":[3,31,42,99,137],"computations":[4,43,100],"on":[5,17,59,124],"modern,":[6],"massively":[7],"parallel":[8,73,118],"systems":[9,125],"with":[10,56,126,140],"GPUs":[11],"and":[12,25,36,83,103,106,120,145],"other":[13],"accelerators":[14],"currently":[15],"relies":[16],"manually-tuned":[18],"coding":[19],"using":[20],"low-level":[21],"approaches":[22],"like":[23],"OpenCL":[24,65,151],"CUDA.":[26],"This":[27],"makes":[28],"development":[29],"applications":[32,134],"a":[33],"complex,":[34],"time-consuming,":[35],"error-prone":[37],"task.":[38],"We":[39,90],"describe":[40,108],"how":[41],"can":[44],"be":[45],"programmed":[46],"in":[47],"our":[48],"SkelCL":[49,62,94,141],"approach":[50],"that":[51,136],"combines":[52],"high-level":[53,69],"programming":[54],"abstractions":[55],"competitive":[57,147],"performance":[58,148],"multi-GPU":[60],"systems.":[61],"extends":[63],"the":[64],"standard":[66],"by":[67],"three":[68,132],"features:":[70],"1)":[71],"pre-implemented":[72],"patterns":[74],"(a.k.a.":[75],"skeletons);":[76],"2)":[77],"container":[78],"data":[79,87],"types":[80],"for":[81,111],"vectors":[82],"matrices;":[84],"3)":[85],"automatic":[86],"(re)distribution":[88],"mechanism.":[89],"introduce":[91],"two":[92],"new":[93],"skeletons":[95],"which":[96],"specifically":[97],"target":[98],"\u2013":[101,105],"MapOverlap":[102],"Stencil":[104],"we":[107],"their":[109,116],"use":[110],"particular":[112],"application":[113],"examples,":[114],"discuss":[115],"efficient":[117],"implementation,":[119],"report":[121],"experimental":[122],"results":[123],"multiple":[127],"GPUs.":[128],"Our":[129],"evaluation":[130],"real-world":[133],"shows":[135],"code":[138],"written":[139],"is":[142],"considerably":[143],"shorter":[144],"offers":[146],"to":[149],"hand-tuned":[150],"code.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}