{"id":"https://openalex.org/W2425283055","doi":null,"title":"Autotuning Sparse Matrix-Vector Multiplication for Multicore","display_name":"Autotuning Sparse Matrix-Vector Multiplication for Multicore","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2425283055","mag":"2425283055"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.6507","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.6507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-215.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5005826143","display_name":"Jong-Ho Byun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jong-Ho Byun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021703621","display_name":"Richard Chun-Hung Lin","orcid":"https://orcid.org/0000-0003-3960-6248","observed_orcids":["https://orcid.org/0000-0003-3960-6248"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Chun-Hung Lin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3960-6248","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091741596","display_name":"Katherine Yelick","orcid":"https://orcid.org/0000-0003-0957-701X","observed_orcids":["https://orcid.org/0000-0003-0957-701X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katherine Yelick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076825233","display_name":"James Weldon Demmel","orcid":"https://orcid.org/0000-0003-1145-3745","observed_orcids":["https://orcid.org/0000-0003-1145-3745"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Demmel","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1145-3745","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1117,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94271938,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"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":0.9945999979972839,"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":0.9945999979972839,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.004399999976158142,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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-vector-multiplication","display_name":"sparse matrix-vector multiplication","score":0.9990000128746033},{"id":"https://openalex.org/keywords/auto-tuning","display_name":"auto-tuning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/multi-core-processors","display_name":"multi-core processors","score":0.9010000228881836},{"id":"https://openalex.org/keywords/sparse-matrix-data-structures","display_name":"sparse matrix data structures","score":0.949999988079071},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"design space exploration","score":0.7039999961853027},{"id":"https://openalex.org/keywords/performance-modeling","display_name":"performance modeling","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191419243812561},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.782152533531189},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6880559325218201},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6672313213348389},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6047536730766296},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5941557884216309},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5907674431800842},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4961181581020355},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4672990143299103},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3351491689682007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09889084100723267},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09655940532684326},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.6507","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.6507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-215.pdf","raw_type":"text"},{"id":"pmh:oai:berkeley.edu:28722-bk0012h760g","doi":null,"is_oa":false,"landing_page_url":"http://techreports.lib.berkeley.edu/accessPages/EECS-2012-215.html","pdf_url":null,"source":{"id":"https://openalex.org/S7407050879","display_name":"UC Berkeley","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I95457486","host_organization_name":"University of California, Berkeley","host_organization_lineage":["https://openalex.org/I95457486"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"technical reports"},{"id":"mag:2425283055","doi":null,"is_oa":false,"landing_page_url":"https://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-215.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W151246516","https://openalex.org/W582073551","https://openalex.org/W1498552948","https://openalex.org/W1499467741","https://openalex.org/W1518969538","https://openalex.org/W1519701134","https://openalex.org/W1527464046","https://openalex.org/W1653630692","https://openalex.org/W1964031104","https://openalex.org/W1972209410","https://openalex.org/W1982733412","https://openalex.org/W2002555321","https://openalex.org/W2014730252","https://openalex.org/W2035080386","https://openalex.org/W2069277577","https://openalex.org/W2089790965","https://openalex.org/W2095420020","https://openalex.org/W2099625934","https://openalex.org/W2114977680","https://openalex.org/W2119296532","https://openalex.org/W2124007994","https://openalex.org/W2126004407","https://openalex.org/W2128853364","https://openalex.org/W2129419431","https://openalex.org/W2130289795","https://openalex.org/W2142356482","https://openalex.org/W2144511445","https://openalex.org/W2148733565","https://openalex.org/W2157146993","https://openalex.org/W2164197394","https://openalex.org/W2167868137","https://openalex.org/W2534294583"],"related_works":["https://openalex.org/W2725757310","https://openalex.org/W2886632348","https://openalex.org/W839792104","https://openalex.org/W2785611382","https://openalex.org/W2751387202","https://openalex.org/W2883093447","https://openalex.org/W1590912170","https://openalex.org/W2128539477","https://openalex.org/W2228597387","https://openalex.org/W4247995867"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4,33,107],"an":[5,57],"important":[6],"kernel":[7],"in":[8,29,114],"scientific":[9],"and":[10,21,44,73,103,129,132],"engineering":[11],"computing.":[12],"Straightforward":[13],"parallel":[14,130],"implementations":[15,74],"of":[16,26,69,94],"SpMV":[17,46,61,77],"often":[18],"perform":[19],"poorly,":[20],"with":[22],"the":[23,39,91,95,104],"increasing":[24],"variety":[25],"architectural":[27,140],"features":[28],"multicore":[30,80],"processors,":[31],"it":[32],"getting":[34],"more":[35],"difficult":[36],"to":[37,75,116,126,135],"determine":[38],"sparse":[40,96],"matrix":[41],"data":[42,71],"structure":[43],"corresponding":[45],"implementation":[47],"that":[48,62,87],"optimize":[49,76],"performance.":[50],"In":[51],"this":[52],"paper":[53],"we":[54],"present":[55],"pOSKI,":[56],"autotuning":[58],"system":[59],"for":[60],"automatically":[63],"searches":[64],"over":[65],"a":[66,84],"large":[67],"set":[68],"possible":[70],"structures":[72],"performance":[78,123,134],"on":[79,89,139],"platforms.":[81],"pOSKI":[82],"explores":[83],"design":[85],"space":[86],"depends":[88],"both":[90],"nonzero":[92],"pattern":[93],"matrix,":[97],"typically":[98],"not":[99],"known":[100],"until":[101],"run-time,":[102],"architecture,":[105],"which":[106],"explored":[108],"off-line":[109],"as":[110,112],"much":[111],"possible,":[113],"order":[115],"reduce":[117],"tuning":[118],"time.":[119],"We":[120],"demonstrate":[121],"significant":[122],"improvements":[124],"compared":[125],"previous":[127],"serial":[128],"implementations,":[131],"compare":[133],"upper":[136],"bounds":[137],"based":[138],"models.":[141]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2016-06-24T00:00:00"}