{"id":"https://openalex.org/W1992303919","doi":"https://doi.org/10.1142/s0129626411000254","title":"HYBRID-PARALLEL SPARSE MATRIX-VECTOR MULTIPLICATION WITH EXPLICIT COMMUNICATION OVERLAP ON CURRENT MULTICORE-BASED SYSTEMS","display_name":"HYBRID-PARALLEL SPARSE MATRIX-VECTOR MULTIPLICATION WITH EXPLICIT COMMUNICATION OVERLAP ON CURRENT MULTICORE-BASED SYSTEMS","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W1992303919","doi":"https://doi.org/10.1142/s0129626411000254","mag":"1992303919"},"language":"en","primary_location":{"id":"doi:10.1142/s0129626411000254","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626411000254","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1106.5908","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067714924","display_name":"G. Schubert","orcid":null},"institutions":[{"id":"https://openalex.org/I36522303","display_name":"Universit\u00e4t Greifswald","ror":"https://ror.org/00r1edq15","country_code":"DE","type":"education","lineage":["https://openalex.org/I36522303"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"GERALD SCHUBERT","raw_affiliation_strings":["Institute of Physics, University of Greifswald, Felix-Hausdorff-Str. 6, 17487 Greifswald, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Physics, University of Greifswald, Felix-Hausdorff-Str. 6, 17487 Greifswald, Germany","institution_ids":["https://openalex.org/I36522303"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056729987","display_name":"Holger Fehske","orcid":"https://orcid.org/0000-0003-2146-8203"},"institutions":[{"id":"https://openalex.org/I36522303","display_name":"Universit\u00e4t Greifswald","ror":"https://ror.org/00r1edq15","country_code":"DE","type":"education","lineage":["https://openalex.org/I36522303"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"HOLGER FEHSKE","raw_affiliation_strings":["Institute of Physics, University of Greifswald, Felix-Hausdorff-Str. 6, 17487 Greifswald, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Physics, University of Greifswald, Felix-Hausdorff-Str. 6, 17487 Greifswald, Germany","institution_ids":["https://openalex.org/I36522303"]}]},{"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, Martensstr. 1, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, 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, Martensstr. 1, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, University of Erlangen-Nuremberg, Martensstr. 1, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2996,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94742297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"21","issue":"03","first_page":"339","last_page":"358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9990000128746033,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.998199999332428,"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":0.8540902137756348},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7961893081665039},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.7503350973129272},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6550318002700806},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5822345018386841},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5094793438911438},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.49006617069244385},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48847758769989014},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.47110632061958313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540902137756348},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7961893081665039},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.7503350973129272},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6550318002700806},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5822345018386841},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5094793438911438},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.49006617069244385},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48847758769989014},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.47110632061958313},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0129626411000254","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626411000254","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:arXiv.org:1106.5908","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1106.5908","pdf_url":"https://arxiv.org/pdf/1106.5908","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1106.5908","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1106.5908","pdf_url":"https://arxiv.org/pdf/1106.5908","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":[{"id":"https://metadata.un.org/sdg/9","score":0.5,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1512455886","https://openalex.org/W1522241184","https://openalex.org/W1556024611","https://openalex.org/W1568530854","https://openalex.org/W1575701986","https://openalex.org/W1680823735","https://openalex.org/W1941137163","https://openalex.org/W1961194538","https://openalex.org/W1975116854","https://openalex.org/W2037783202","https://openalex.org/W2049585661","https://openalex.org/W2062240003","https://openalex.org/W2092013581","https://openalex.org/W2095420020","https://openalex.org/W2103877122","https://openalex.org/W2111667319","https://openalex.org/W2138782497","https://openalex.org/W3025552668","https://openalex.org/W4230252700","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2293771254","https://openalex.org/W2119413962","https://openalex.org/W2030992542","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W4221142455","https://openalex.org/W2032786851","https://openalex.org/W2914631005","https://openalex.org/W2952630098","https://openalex.org/W3132517792"],"abstract_inverted_index":{"We":[0,115],"evaluate":[1],"optimized":[2],"parallel":[3,43],"sparse":[4,44],"matrix-vector":[5,45],"operations":[6,46],"for":[7,119],"several":[8],"representative":[9],"application":[10],"areas":[11],"on":[12,92,132],"widespread":[13],"multicore-based":[14,135],"cluster":[15,136],"configurations.":[16],"First":[17],"the":[18,37,40,55,122],"single-socket":[19],"baseline":[20],"performance":[21,41,99,117],"is":[22,47,60],"analyzed":[23],"and":[24,78,129,137],"modeled":[25],"with":[26],"respect":[27],"to":[28,63,106],"basic":[29],"architectural":[30],"properties":[31],"of":[32,42,76,101],"standard":[33,68],"multicore":[34],"chips.":[35],"Beyond":[36],"single":[38],"node,":[39],"often":[48],"limited":[49],"by":[50,83],"communication":[51,65,77,87,113],"overhead.":[52],"Starting":[53],"from":[54],"observation":[56],"that":[57,73],"nonblocking":[58],"MPI":[59,69],"not":[61],"able":[62],"hide":[64],"cost":[66],"using":[67,84],"implementations,":[70],"we":[71,97],"demonstrate":[72],"explicit":[74,112,130],"overlap":[75,131],"computation":[79],"can":[80],"be":[81],"achieved":[82],"a":[85,93,133,138],"dedicated":[86],"thread,":[88],"which":[89],"may":[90],"run":[91],"virtual":[94],"core.":[95],"Moreover":[96],"identify":[98],"benefits":[100],"hybrid":[102,126],"MPI/OpenMP":[103],"programming":[104,127],"due":[105],"improved":[107],"load":[108],"balancing":[109],"even":[110],"without":[111],"overlap.":[114],"compare":[116],"results":[118],"pure":[120],"MPI,":[121],"widely":[123],"used":[124],"\"vector-like\"":[125],"strategies,":[128],"modern":[134],"Cray":[139],"XE6":[140],"system.":[141]},"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":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}