{"id":"https://openalex.org/W2129050115","doi":"https://doi.org/10.1109/ipdpsw.2010.5470813","title":"Multicore-aware parallel temporal blocking of stencil codes for shared and distributed memory","display_name":"Multicore-aware parallel temporal blocking of stencil codes for shared and distributed memory","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2129050115","doi":"https://doi.org/10.1109/ipdpsw.2010.5470813","mag":"2129050115"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2010.5470813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/0912.4506","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":"education","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","Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, 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":"education","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","Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","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":"education","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","Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9997000098228455,"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":0.8358460664749146},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.8163843750953674},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7217996716499329},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6939088106155396},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.6934429407119751},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5896058082580566},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5328420400619507},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.46843084692955017},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4219365119934082},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40579938888549805},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12958988547325134},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11382946372032166},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.10842189192771912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8358460664749146},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8163843750953674},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7217996716499329},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6939088106155396},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.6934429407119751},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5896058082580566},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5328420400619507},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.46843084692955017},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4219365119934082},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40579938888549805},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12958988547325134},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11382946372032166},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.10842189192771912},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ipdpsw.2010.5470813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:0912.4506","is_oa":true,"landing_page_url":"http://arxiv.org/abs/0912.4506","pdf_url":"https://arxiv.org/pdf/0912.4506","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.745.6765","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.745.6765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/0912.4506.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:0912.4506","is_oa":true,"landing_page_url":"http://arxiv.org/abs/0912.4506","pdf_url":"https://arxiv.org/pdf/0912.4506","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W292088311","https://openalex.org/W1542625977","https://openalex.org/W1968013322","https://openalex.org/W2108730477","https://openalex.org/W2128746953","https://openalex.org/W2129471558","https://openalex.org/W2150319905","https://openalex.org/W2154786353","https://openalex.org/W2155967587","https://openalex.org/W2160106616","https://openalex.org/W2167713801","https://openalex.org/W3152199537","https://openalex.org/W6632644488","https://openalex.org/W6684745099"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W4205439893","https://openalex.org/W2150064838","https://openalex.org/W1933089384","https://openalex.org/W2185094550","https://openalex.org/W2088823210"],"abstract_inverted_index":{"New":[0],"algorithms":[1],"and":[2,55,58],"optimization":[3],"techniques":[4],"are":[5],"needed":[6],"to":[7],"balance":[8],"the":[9,21,33,36],"accelerating":[10],"trend":[11],"towards":[12],"bandwidth-starved":[13],"multicore":[14,53],"chips.":[15],"It":[16],"is":[17],"well":[18],"known":[19],"that":[20,45],"performance":[22],"of":[23,49,63],"stencil":[24],"codes":[25],"can":[26,71],"be":[27,72],"improved":[28],"by":[29],"temporal":[30,69],"blocking,":[31],"lessening":[32],"pressure":[34],"on":[35],"memory":[37],"interface.":[38],"We":[39],"introduce":[40],"a":[41,76],"new":[42],"pipelined":[43],"approach":[44],"makes":[46],"explicit":[47],"use":[48],"shared":[50],"caches":[51],"in":[52,75],"environments":[54],"minimizes":[56],"synchronization":[57],"boundary":[59],"overhead.":[60],"For":[61],"clusters":[62],"shared-memory":[64],"nodes":[65],"we":[66],"demonstrate":[67],"how":[68],"blocking":[70],"employed":[73],"successfully":[74],"hybrid":[77],"shared/distributed-memory":[78],"environment.":[79]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}