{"id":"https://openalex.org/W2143844951","doi":"https://doi.org/10.1109/hpcsim.2013.6641452","title":"Model-guided performance analysis of the sparse matrix-matrix multiplication","display_name":"Model-guided performance analysis of the sparse matrix-matrix multiplication","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2143844951","doi":"https://doi.org/10.1109/hpcsim.2013.6641452","mag":"2143844951"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2013.6641452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2013.6641452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-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/A5025655589","display_name":"Tobias Scharpff","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":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tobias Scharpff","raw_affiliation_strings":["Chair for System Simulation, University of Erlangen-Nuremberg, Erlangen, Germany","Dept. for Syst. Simulation, Univ. Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Chair for System Simulation, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Dept. for Syst. Simulation, Univ. Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041892220","display_name":"Klaus Iglberger","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":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Iglberger","raw_affiliation_strings":["Chair for System Simulation, University of Erlangen-Nuremberg, Erlangen, Germany","Dept. for Syst. Simulation, Univ. Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Chair for System Simulation, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Dept. for Syst. Simulation, Univ. 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":"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 Comput. Center, Univ. Erlangen-Nuremberg, Erlangen, Germany"],"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 Comput. Center, Univ. Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109197540","display_name":"Ulrich R\u00fcde","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":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulrich Rude","raw_affiliation_strings":["Chair for System Simulation, University of Erlangen-Nuremberg, Erlangen, Germany","Dept. for Syst. Simulation, Univ. Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Chair for System Simulation, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Dept. for Syst. Simulation, Univ. Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025655589"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.3152,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63271137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"445","last_page":"452"},"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":0.9990000128746033,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980000257492065,"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/sparse-matrix","display_name":"Sparse matrix","score":0.7795141339302063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7497332096099854},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6464438438415527},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.569054365158081},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5411819815635681},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5348801612854004},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5061063170433044},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4547419548034668},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4514247477054596},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3739883601665497},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3364107012748718},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3350106179714203},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1463533341884613},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09993964433670044}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7795141339302063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497332096099854},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6464438438415527},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.569054365158081},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5411819815635681},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5348801612854004},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5061063170433044},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4547419548034668},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4514247477054596},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3739883601665497},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3364107012748718},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3350106179714203},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1463533341884613},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09993964433670044},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcsim.2013.6641452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2013.6641452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W72635156","https://openalex.org/W1483773184","https://openalex.org/W1522241184","https://openalex.org/W1575701986","https://openalex.org/W1665019326","https://openalex.org/W1992303919","https://openalex.org/W1997882689","https://openalex.org/W2002555321","https://openalex.org/W2043609983","https://openalex.org/W2089437293","https://openalex.org/W2096642134","https://openalex.org/W2103877122","https://openalex.org/W2139316564","https://openalex.org/W3099775292","https://openalex.org/W4214826206","https://openalex.org/W6987404413"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W4239424132","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2086123442"],"abstract_inverted_index":{"Achieving":[0],"high":[1,137],"efficiency":[2,111],"with":[3,120,139],"numerical":[4],"kernels":[5,86,119],"for":[6,53,99,168],"sparse":[7,66,83,147],"matrices":[8],"is":[9,69],"of":[10,17,26,45,47,60,70,82,112,136,163],"utmost":[11],"importance,":[12],"since":[13],"they":[14],"are":[15,50,157],"part":[16],"many":[18],"simulation":[19,39],"codes":[20],"and":[21,31,43,58,105],"tend":[22],"to":[23,108],"use":[24,46,106],"most":[25,169],"the":[27,41,54,65,79,88,101,110,134,145,164],"available":[28],"compute":[29],"time":[30],"resources.":[32],"In":[33,62,73],"addition,":[34],"especially":[35],"in":[36,87],"large":[37],"scale":[38],"frameworks":[40],"readability":[42],"ease":[44],"mathematical":[48],"expressions":[49],"essential":[51],"components":[52],"continuous":[55],"maintenance,":[56],"modification,":[57],"extension":[59],"software.":[61],"this":[63,74],"context,":[64],"matrix-matrix":[67,84],"multiplication":[68,85],"special":[71],"interest.":[72],"paper":[75],"we":[76,116,152],"thoroughly":[77],"analyze":[78],"single-core":[80],"performance":[81,138],"Blaze":[89],"Smart":[90],"Expression":[91],"Template":[92],"(SET)":[93],"framework.":[94],"We":[95],"develop":[96],"simple":[97],"models":[98],"estimating":[100],"achievable":[102],"maximum":[103],"performance,":[104],"them":[107],"assess":[109],"our":[113,155],"implementations.":[114],"Additionally,":[115],"compare":[117],"these":[118],"several":[121],"commonly":[122],"used":[123],"SET-based":[124],"C++":[125],"libraries,":[126],"which,":[127],"just":[128],"as":[129],"Blaze,":[130],"aim":[131],"at":[132],"combining":[133],"requirements":[135],"an":[140],"elegant":[141],"user":[142],"interface.":[143],"For":[144],"different":[146],"matrix":[148],"structures":[149],"considered":[150],"here,":[151],"show":[153],"that":[154],"implementations":[156],"competitive":[158],"or":[159],"faster":[160],"than":[161],"those":[162],"other":[165],"SET":[166],"libraries":[167],"problem":[170],"sizes":[171],"on":[172],"a":[173],"current":[174],"Intel":[175],"multicore":[176],"processor.":[177]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
