{"id":"https://openalex.org/W2135063202","doi":"https://doi.org/10.1109/ipdps.2009.5161159","title":"Exploring the effect of block shapes on the performance of sparse kernels","display_name":"Exploring the effect of block shapes on the performance of sparse kernels","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2135063202","doi":"https://doi.org/10.1109/ipdps.2009.5161159","mag":"2135063202"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2009.5161159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5161159","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":true,"oa_status":"green","oa_url":"http://doi.org/10.1109/IPDPS.2009.5161159","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030151853","display_name":"Vasileios Karakasis","orcid":"https://orcid.org/0000-0003-1063-9855"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vasileios Karakasis","raw_affiliation_strings":["Computing Systems Laboratory, National and Technical University of Athens, Greece","Computing Systems Laboratory, National Technical University of Athens, Greece#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Systems Laboratory, National and Technical University of Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Computing Systems Laboratory, National Technical University of Athens, Greece#TAB#","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023870696","display_name":"Georgios Goumas","orcid":"https://orcid.org/0000-0001-7811-4831"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Goumas","raw_affiliation_strings":["Computing Systems Laboratory, National and Technical University of Athens, Greece","Computing Systems Laboratory, National Technical University of Athens, Greece#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Systems Laboratory, National and Technical University of Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Computing Systems Laboratory, National Technical University of Athens, Greece#TAB#","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023526161","display_name":"Nectarios Koziris","orcid":"https://orcid.org/0000-0002-4890-8427"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nectarios Koziris","raw_affiliation_strings":["Computing Systems Laboratory, National and Technical University of Athens, Greece","Computing Systems Laboratory, National Technical University of Athens, Greece#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Systems Laboratory, National and Technical University of Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Computing Systems Laboratory, National Technical University of Athens, Greece#TAB#","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174458059"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3726","issue":null,"first_page":"1","last_page":"8"},"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/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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9961000084877014,"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":0.8154725432395935},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8128899335861206},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.717997133731842},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.7113291025161743},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.5649621486663818},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5304032564163208},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.48151645064353943},{"id":"https://openalex.org/keywords/block-size","display_name":"Block size","score":0.4795917570590973},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.43314066529273987},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09699007868766785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08109179139137268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8154725432395935},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8128899335861206},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.717997133731842},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.7113291025161743},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.5649621486663818},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5304032564163208},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.48151645064353943},{"id":"https://openalex.org/C41431624","wikidata":"https://www.wikidata.org/wiki/Q1053357","display_name":"Block size","level":3,"score":0.4795917570590973},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.43314066529273987},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09699007868766785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08109179139137268},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ipdps.2009.5161159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5161159","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.495.7170","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.495.7170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslab.ece.ntua.gr/~goumas/downloads/pdsec2009.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.591.4311","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.591.4311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslab.ece.ntua.gr/~bkk/files/papers/pdsec09.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/32574","is_oa":true,"landing_page_url":"http://doi.org/10.1109/IPDPS.2009.5161159","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/32574","is_oa":true,"landing_page_url":"http://doi.org/10.1109/IPDPS.2009.5161159","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1207115811","https://openalex.org/W1518969538","https://openalex.org/W1538642953","https://openalex.org/W1575701986","https://openalex.org/W1596846800","https://openalex.org/W1884140786","https://openalex.org/W1965551736","https://openalex.org/W1990832096","https://openalex.org/W2098602979","https://openalex.org/W2099625934","https://openalex.org/W2114977680","https://openalex.org/W2146530035","https://openalex.org/W2164139896","https://openalex.org/W3138705879","https://openalex.org/W6639344521"],"related_works":["https://openalex.org/W2132428222","https://openalex.org/W2022842990","https://openalex.org/W2914086833","https://openalex.org/W2002443693","https://openalex.org/W1541167181","https://openalex.org/W4389888442","https://openalex.org/W2149529325","https://openalex.org/W1511230764","https://openalex.org/W3103168911","https://openalex.org/W2137534299"],"abstract_inverted_index":{"In":[0,135],"this":[1,136],"paper":[2,137],"we":[3,138],"explore":[4,139],"the":[5,8,17,35,57,62,69,89,106,113,129,133,142],"impact":[6],"of":[7,16,34,51,59,82,132,145],"block":[9,90,157],"shape":[10],"on":[11,48,61],"blocked":[12,64,83],"and":[13,23,67,73,77,121,140],"vectorized":[14],"versions":[15],"Sparse":[18,44],"Matrix-Vector":[19],"Multiplication":[20],"(SpMV)":[21],"kernel":[22,66],"build":[24],"upon":[25],"previous":[26],"work":[27],"by":[28],"performing":[29],"an":[30],"extensive":[31],"experimental":[32],"evaluation":[33],"most":[36],"widespread":[37],"blocking":[38],"storage":[39],"format,":[40,47],"namely":[41],"Block":[42],"Compressed":[43],"Row":[45],"(BCSR)":[46],"a":[49],"set":[50],"modern":[52,146],"commodity":[53,147],"microarchitectures.":[54],"We":[55],"evaluate":[56],"merit":[58],"vectorization":[60],"memory-bound":[63],"SpMV":[65,84],"report":[68],"results":[70],"for":[71,97,152],"single-":[72],"multithreaded":[74],"(both":[75],"SMP":[76],"NUMA)":[78],"configurations.":[79],"The":[80],"performance":[81,154],"can":[85],"significantly":[86],"vary":[87],"with":[88],"shape,":[91],"despite":[92],"similar":[93],"memory":[94,114],"bandwidth":[95],"demands":[96],"different":[98],"blocks.":[99],"This":[100],"is":[101],"further":[102],"accentuated":[103],"when":[104],"vectorizing":[105],"kernel.":[107,134],"When":[108],"moving":[109],"to":[110],"multiple":[111],"cores,":[112],"wall":[115],"problem":[116],"becomes":[117],"even":[118],"more":[119],"evident":[120],"may":[122],"overwhelm":[123],"any":[124],"benefit":[125],"from":[126],"optimizations":[127],"targeting":[128],"computational":[130],"part":[131],"discuss":[141],"architectural":[143],"characteristics":[144],"architectures":[148],"that":[149],"are":[150],"responsible":[151],"these":[153],"variations":[155],"between":[156],"shapes.":[158]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
