{"id":"https://openalex.org/W2150319905","doi":"https://doi.org/10.1109/compsac.2009.82","title":"Efficient Temporal Blocking for Stencil Computations by Multicore-Aware Wavefront Parallelization","display_name":"Efficient Temporal Blocking for Stencil Computations by Multicore-Aware Wavefront Parallelization","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2150319905","doi":"https://doi.org/10.1109/compsac.2009.82","mag":"2150319905"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/compsac.2009.82","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112049374","display_name":"Thomas Zeiser","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Zeiser","raw_affiliation_strings":["Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003949750","display_name":"Markus Wittmann","orcid":"https://orcid.org/0000-0002-4812-9052"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Wittmann","raw_affiliation_strings":["Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108081461","display_name":"Holger Fehske","orcid":null},"institutions":[{"id":"https://openalex.org/I36522303","display_name":"Universit\u00e4t Greifswald","ror":"https://ror.org/00r1edq15","country_code":"DE","type":"funder","lineage":["https://openalex.org/I36522303"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Holger Fehske","raw_affiliation_strings":["Institute of Theoretical Physics, University of Greifswald, Greifswald, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Theoretical Physics, University of Greifswald, Greifswald, Germany","institution_ids":["https://openalex.org/I36522303"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.232,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":117,"citation_normalized_percentile":{"value":0.980831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997,"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":0.9997,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9927,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9913,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9203211},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.7656981},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.58714277}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9203211},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8841537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81494284},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.7656981},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.60114086},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.58714277},{"id":"https://openalex.org/C165699331","wikidata":"https://www.wikidata.org/wiki/Q461533","display_name":"Wavefront","level":2,"score":0.5703283},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5694648},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2662291},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20590699},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.074563},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.061422855},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/compsac.2009.82","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":7,"referenced_works":["https://openalex.org/W1480947737","https://openalex.org/W2095875205","https://openalex.org/W2114921633","https://openalex.org/W2128746953","https://openalex.org/W2154786353","https://openalex.org/W2155967587","https://openalex.org/W3152199537"],"related_works":["https://openalex.org/W76123042","https://openalex.org/W4376632753","https://openalex.org/W4226283508","https://openalex.org/W3091752332","https://openalex.org/W2560653225","https://openalex.org/W2488897859","https://openalex.org/W2150319905","https://openalex.org/W2111914791","https://openalex.org/W1972447202","https://openalex.org/W1547833503"],"abstract_inverted_index":{"We":[0,55],"present":[1],"a":[2,11,23,28,50,64],"pipelined":[3],"wavefront":[4],"parallelization":[5,44],"approach":[6,75],"for":[7],"stencil-based":[8,67],"computations.":[9],"Within":[10],"fixed":[12],"spatial":[13],"domain":[14],"successive":[15,40],"wavefronts":[16,41],"are":[17],"executed":[18],"by":[19],"threads":[20],"scheduled":[21],"to":[22],"multicore":[24],"processor":[25],"chip":[26],"with":[27],"shared":[29],"outer":[30],"level":[31],"cache.":[32],"By":[33],"re-using":[34],"data":[35],"from":[36],"cache":[37],"in":[38,49,60],"the":[39,57,71,77],"this":[42],"multicore-aware":[43],"strategy":[45],"employs":[46],"temporal":[47],"blocking":[48],"simple":[51],"and":[52,69,84],"efficient":[53],"way.":[54],"use":[56],"Jacobi":[58],"algorithm":[59],"three":[61],"dimensions":[62],"as":[63],"prototype":[65],"or":[66],"computations":[68],"prove":[70],"efficiency":[72],"of":[73,80],"our":[74],"on":[76],"latest":[78],"generations":[79],"Intel's":[81],"times86":[82],"quad-":[83],"hexa-core":[85],"processors.":[86]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2150319905","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":10}],"updated_date":"2025-03-18T23:11:55.217581","created_date":"2016-06-24"}