{"id":"https://openalex.org/W2141374519","doi":"https://doi.org/10.1177/1094342007083801","title":"Performance Optimization and Modeling of Blocked Sparse Kernels","display_name":"Performance Optimization and Modeling of Blocked Sparse Kernels","publication_year":2007,"publication_date":"2007-10-29","ids":{"openalex":"https://openalex.org/W2141374519","doi":"https://doi.org/10.1177/1094342007083801","mag":"2141374519"},"language":"en","primary_location":{"id":"doi:10.1177/1094342007083801","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342007083801","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-02421133","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082594621","display_name":"Alfredo Buttari","orcid":"https://orcid.org/0000-0003-3207-7021"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["FR","US"],"is_corresponding":true,"raw_author_name":"Alfredo Buttari","raw_affiliation_strings":["INNOVATIVE COMPUTING LABORATORY, UNIVERSITY OF TENNESSEE, KNOXVILLE, TN,","CNRS - Centre National de la Recherche Scientifique (France)"],"affiliations":[{"raw_affiliation_string":"INNOVATIVE COMPUTING LABORATORY, UNIVERSITY OF TENNESSEE, KNOXVILLE, TN,","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"CNRS - Centre National de la Recherche Scientifique (France)","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036842144","display_name":"Victor Eijkhout","orcid":"https://orcid.org/0000-0002-8094-5738"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor Eijkhout","raw_affiliation_strings":["TEXAS ADVANCED COMPUTING LABORATORY, THE UNIVERSITY OF TEXAS AT AUSTIN","Texas Advanced Computing Center, The University of Texas at Austin, Austin, Texas (France)"],"affiliations":[{"raw_affiliation_string":"TEXAS ADVANCED COMPUTING LABORATORY, THE UNIVERSITY OF TEXAS AT AUSTIN","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Texas Advanced Computing Center, The University of Texas at Austin, Austin, Texas (France)","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020584809","display_name":"Julien Langou","orcid":"https://orcid.org/0000-0002-7803-1822"},"institutions":[{"id":"https://openalex.org/I4210087413","display_name":"University of Colorado Health","ror":"https://ror.org/0107w4315","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210087413"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julien Langou","raw_affiliation_strings":["DEPARTMENT OF MATHEMATICAL SCIENCES, UNIVERSITY OF COLORADO AT DENVER AND\r                        HEALTH SCIENCES CENTER, CO","Department of Mathematical and Statistical Sciences (Campus Box 170, P.O. Box 173364, Denver, Colorado 80217-3364, USA - United States)"],"affiliations":[{"raw_affiliation_string":"DEPARTMENT OF MATHEMATICAL SCIENCES, UNIVERSITY OF COLORADO AT DENVER AND\r                        HEALTH SCIENCES CENTER, CO","institution_ids":["https://openalex.org/I4210087413"]},{"raw_affiliation_string":"Department of Mathematical and Statistical Sciences (Campus Box 170, P.O. Box 173364, Denver, Colorado 80217-3364, USA - United States)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031298177","display_name":"Salvatore Filippone","orcid":"https://orcid.org/0000-0002-5859-7538"},"institutions":[{"id":"https://openalex.org/I116067653","display_name":"University of Rome Tor Vergata","ror":"https://ror.org/02p77k626","country_code":"IT","type":"education","lineage":["https://openalex.org/I116067653"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Salvatore Filippone","raw_affiliation_strings":["TOR VERGATA UNIVERSITY, ROME, ITALY","University of Rome 'Tor Vergeta' (Italy)"],"affiliations":[{"raw_affiliation_string":"TOR VERGATA UNIVERSITY, ROME, ITALY","institution_ids":["https://openalex.org/I116067653"]},{"raw_affiliation_string":"University of Rome 'Tor Vergeta' (Italy)","institution_ids":["https://openalex.org/I116067653"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082594621"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":3.1666,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9179839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"4","first_page":"467","last_page":"484"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993000030517578,"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":0.9975000023841858,"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":0.7350516319274902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6861032843589783},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.675213098526001},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.6381784081459045},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.614060640335083},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5547468066215515},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5186938047409058},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.501591682434082},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4880763292312622},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4545646011829376},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42019665241241455},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.35727447271347046},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3437572717666626},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20202240347862244},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17214247584342957},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09437307715415955},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07609453797340393},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07087194919586182},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06329914927482605}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7350516319274902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6861032843589783},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.675213098526001},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.6381784081459045},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.614060640335083},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5547468066215515},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5186938047409058},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.501591682434082},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4880763292312622},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4545646011829376},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42019665241241455},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35727447271347046},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3437572717666626},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20202240347862244},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17214247584342957},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09437307715415955},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07609453797340393},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07087194919586182},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06329914927482605},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/1094342007083801","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342007083801","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02421133v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02421133","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"International Journal of High Performance Computing Applications, 2016, 21 (4), pp.467-484. &#x27E8;10.1177/1094342007083801&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02421133v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02421133","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"International Journal of High Performance Computing Applications, 2016, 21 (4), pp.467-484. &#x27E8;10.1177/1094342007083801&#x27E9;","raw_type":"Journal articles"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"id":"https://openalex.org/F4320315068","display_name":"University of Tennessee, Knoxville","ror":"https://ror.org/020f3ap87"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1481131999","https://openalex.org/W1575701986","https://openalex.org/W1964031104","https://openalex.org/W1992107487","https://openalex.org/W2068543948","https://openalex.org/W2070299075","https://openalex.org/W2099625934","https://openalex.org/W2114977680","https://openalex.org/W2130289795","https://openalex.org/W2166210624","https://openalex.org/W2167868137","https://openalex.org/W2400300130","https://openalex.org/W4245503759","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2744553356","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W3202552726","https://openalex.org/W2279642117","https://openalex.org/W4321636545","https://openalex.org/W2023476765"],"abstract_inverted_index":{"We":[0,53],"present":[1,54],"a":[2,23,31,40,55,65],"method":[3],"for":[4,19],"automatically":[5],"selecting":[6],"optimal":[7,50],"implementations":[8],"of":[9,42,68],"sparse":[10,45],"matrix-vector":[11],"operations.":[12],"Our":[13],"software":[14],"\u201cAcCELS\u201d":[15],"(Accelerated":[16],"Compress-storage":[17],"Elements":[18],"Linear":[20],"Solvers)":[21],"involves":[22],"setup":[24],"phase":[25,33],"that":[26,58],"probes":[27],"machine":[28],"characteristics,":[29],"and":[30],"run-time":[32],"where":[34],"stored":[35],"characteristics":[36],"are":[37],"combined":[38],"with":[39],"measure":[41],"the":[43,49],"actual":[44],"matrix":[46],"to":[47,61],"find":[48],"kernel":[51],"implementation.":[52],"performance":[56],"model":[57],"is":[59],"shown":[60],"be":[62],"accurate":[63],"over":[64],"large":[66],"range":[67],"matrices.":[69]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
