{"id":"https://openalex.org/W2157685422","doi":"https://doi.org/10.1109/ipdps.2009.5161031","title":"Parallel data-locality aware stencil computations on modern micro-architectures","display_name":"Parallel data-locality aware stencil computations on modern micro-architectures","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2157685422","doi":"https://doi.org/10.1109/ipdps.2009.5161031","mag":"2157685422"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2009.5161031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5161031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel &amp; Distributed Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047169841","display_name":"Matthias Christen","orcid":"https://orcid.org/0000-0001-7724-4562"},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matthias Christen","raw_affiliation_strings":["High Performance and Web Computing Group, Computer Science Department, University of Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High Performance and Web Computing Group, Computer Science Department, University of Basel, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017590193","display_name":"Olaf Schenk","orcid":"https://orcid.org/0000-0001-8636-1023"},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Olaf Schenk","raw_affiliation_strings":["High Performance and Web Computing Group, Computer Science Department, University of Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High Performance and Web Computing Group, Computer Science Department, University of Basel, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086002238","display_name":"Esra Neufeld","orcid":"https://orcid.org/0000-0001-5528-6147"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I4210086584","display_name":"Foundation for Research on Information Technologies in Society","ror":"https://ror.org/0014xm371","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I4210086584"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Esra Neufeld","raw_affiliation_strings":["ITIS Foundation, ETH Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITIS Foundation, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088","https://openalex.org/I4210086584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050123014","display_name":"Peter Messmer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156081","display_name":"Tech-X Corporation (United States)","ror":"https://ror.org/04n0rvp85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210156081"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Messmer","raw_affiliation_strings":["Tech-X Corporation, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tech-X Corporation, Boulder, CO, USA","institution_ids":["https://openalex.org/I4210156081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111626869","display_name":"Helmar Burkhart","orcid":null},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Helmar Burkhart","raw_affiliation_strings":["High Performance and Web Computing Group, Computer Science Department, University of Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High Performance and Web Computing Group, Computer Science Department, University of Basel, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5606,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91084053,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2073","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9948999881744385,"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":0.9948999881744385,"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":0.987500011920929,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.9495970606803894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8228943347930908},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7889978885650635},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7111796140670776},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6496126651763916},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6033814549446106},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.559721827507019},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5197436809539795},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.508560061454773},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.47913381457328796},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4524775743484497},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.44681859016418457},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42476823925971985},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3850381374359131},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.1760256290435791},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1436428427696228},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.12586259841918945},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08258682489395142}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9495970606803894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228943347930908},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7889978885650635},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7111796140670776},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6496126651763916},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6033814549446106},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.559721827507019},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5197436809539795},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.508560061454773},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.47913381457328796},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4524775743484497},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.44681859016418457},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42476823925971985},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3850381374359131},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.1760256290435791},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1436428427696228},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.12586259841918945},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08258682489395142},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":1,"locations":[{"id":"doi:10.1109/ipdps.2009.5161031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5161031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel &amp; Distributed Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1487278226","https://openalex.org/W1549556853","https://openalex.org/W1549990549","https://openalex.org/W1825294837","https://openalex.org/W1948181060","https://openalex.org/W1963540754","https://openalex.org/W1964639877","https://openalex.org/W1967264375","https://openalex.org/W1968013322","https://openalex.org/W1997147891","https://openalex.org/W2003017040","https://openalex.org/W2027829941","https://openalex.org/W2113614699","https://openalex.org/W2116762028","https://openalex.org/W2119042753","https://openalex.org/W2138181577","https://openalex.org/W2140422614","https://openalex.org/W2153092996","https://openalex.org/W4239526824","https://openalex.org/W6632862924"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W2583128298","https://openalex.org/W2053359564","https://openalex.org/W2161159383","https://openalex.org/W1495260638","https://openalex.org/W1511204342","https://openalex.org/W2369125128","https://openalex.org/W2369223577","https://openalex.org/W2010020348","https://openalex.org/W2010557350"],"abstract_inverted_index":{"Novel":[0],"micro-architectures":[1],"including":[2],"the":[3,26,38,56,68,72,83,95],"Cell":[4,39],"Broadband":[5],"Engine":[6],"Architecture":[7],"and":[8,32,41,43,86],"graphics":[9],"processing":[10],"units":[11],"are":[12],"attractive":[13],"platforms":[14],"for":[15],"compute-intensive":[16],"simulations.":[17],"This":[18],"paper":[19],"focuses":[20],"on":[21,36,49,99],"stencil":[22,61],"computations":[23],"arising":[24],"in":[25],"context":[27],"of":[28,60,67,71,94],"a":[29,47,50,65],"biomedical":[30],"simulation":[31],"presents":[33],"performance":[34,70,89,100],"benchmarks":[35],"both":[37],"BE":[40],"GPUs":[42],"contrasts":[44],"them":[45],"with":[46],"benchmark":[48],"traditional":[51],"CPU":[52,103],"system.":[53],"Due":[54],"to":[55],"low":[57],"arithmetic":[58],"intensity":[59],"computations,":[62],"typically":[63],"only":[64],"fraction":[66],"peak":[69],"compute":[73],"hardware":[74],"is":[75,79],"reached.":[76],"An":[77],"algorithm":[78],"presented,":[80],"which":[81],"reduces":[82],"bandwidth":[84],"requirements":[85],"thereby":[87],"improves":[88],"by":[90],"exploiting":[91],"temporal":[92],"locality":[93],"data.":[96],"We":[97],"report":[98],"improvements":[101],"over":[102],"implementations.":[104]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
