{"id":"https://openalex.org/W2001175489","doi":"https://doi.org/10.1587/elex.10.20130147","title":"Breaking the performance bottleneck of sparse matrix-vector multiplication on SIMD processors","display_name":"Breaking the performance bottleneck of sparse matrix-vector multiplication on SIMD processors","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2001175489","doi":"https://doi.org/10.1587/elex.10.20130147","mag":"2001175489"},"language":"en","primary_location":{"id":"doi:10.1587/elex.10.20130147","is_oa":true,"landing_page_url":"https://doi.org/10.1587/elex.10.20130147","pdf_url":"https://www.jstage.jst.go.jp/article/elex/10/9/10_10.20130147/_pdf","source":{"id":"https://openalex.org/S207433681","display_name":"IEICE Electronics Express","issn_l":"1349-2543","issn":["1349-2543","1349-9467"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Electronics Express","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.jstage.jst.go.jp/article/elex/10/9/10_10.20130147/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066576755","display_name":"Kai Zhang","orcid":"https://orcid.org/0000-0003-1306-5586"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Zhang","raw_affiliation_strings":["School of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644317","display_name":"Shuming Chen","orcid":"https://orcid.org/0000-0003-4441-2202"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuming Chen","raw_affiliation_strings":["School of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101877535","display_name":"Yaohua Wang","orcid":"https://orcid.org/0000-0002-9556-5535"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaohua Wang","raw_affiliation_strings":["School of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109218335","display_name":"Jianghua Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghua Wan","raw_affiliation_strings":["School of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066576755"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.3171,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58999311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":"9","first_page":"20130147","last_page":"20130147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987999796867371,"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":0.9976000189781189,"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/simd","display_name":"SIMD","score":0.9142037630081177},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8429095149040222},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8274608850479126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7626174688339233},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6839550733566284},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6132792830467224},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5890437960624695},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5762262344360352},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5163032412528992},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4691395163536072},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4452390670776367},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12961161136627197},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.08920720219612122}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9142037630081177},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8429095149040222},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8274608850479126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626174688339233},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6839550733566284},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6132792830467224},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5890437960624695},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5762262344360352},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5163032412528992},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4691395163536072},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4452390670776367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12961161136627197},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.08920720219612122},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/elex.10.20130147","is_oa":true,"landing_page_url":"https://doi.org/10.1587/elex.10.20130147","pdf_url":"https://www.jstage.jst.go.jp/article/elex/10/9/10_10.20130147/_pdf","source":{"id":"https://openalex.org/S207433681","display_name":"IEICE Electronics Express","issn_l":"1349-2543","issn":["1349-2543","1349-9467"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Electronics Express","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/elex.10.20130147","is_oa":true,"landing_page_url":"https://doi.org/10.1587/elex.10.20130147","pdf_url":"https://www.jstage.jst.go.jp/article/elex/10/9/10_10.20130147/_pdf","source":{"id":"https://openalex.org/S207433681","display_name":"IEICE Electronics Express","issn_l":"1349-2543","issn":["1349-2543","1349-9467"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Electronics Express","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6505718541","display_name":null,"funder_award_id":"61070036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2001175489.pdf","grobid_xml":"https://content.openalex.org/works/W2001175489.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1982008951","https://openalex.org/W1990832096","https://openalex.org/W2027718011","https://openalex.org/W2076135443","https://openalex.org/W2098513105","https://openalex.org/W2128853364","https://openalex.org/W2402171240"],"related_works":["https://openalex.org/W1560663560","https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W1993644742","https://openalex.org/W1509422975","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W4239424132"],"abstract_inverted_index":{"The":[0,53,94],"low":[1],"utilization":[2],"of":[3,25,48,84],"SIMD":[4,15,51],"units":[5],"and":[6,33,66],"memory":[7],"bandwidth":[8],"is":[9,23],"the":[10,26,45,92],"main":[11],"performance":[12,46],"bottleneck":[13,47],"on":[14,50],"processors":[16],"for":[17,90],"sparse":[18,58],"matrix-vector":[19],"multiplication":[20],"(SpMV),":[21],"which":[22],"one":[24],"most":[27],"important":[28],"kernels":[29],"in":[30],"many":[31],"scientific":[32],"engineering":[34],"applications.":[35],"This":[36],"paper":[37],"proposes":[38],"a":[39,56,62,67],"hybrid":[40,76],"optimization":[41,77],"method":[42,54,78],"to":[43,100],"break":[44],"SpMV":[49,64],"processors.":[52],"includes":[55],"new":[57],"matrix":[59],"compressed":[60],"format,":[61],"block":[63],"algorithm,":[65],"vector":[68,88],"write":[69],"buffer.":[70],"Experimental":[71],"results":[72],"show":[73],"that":[74],"our":[75],"can":[79,97],"achieve":[80],"an":[81],"average":[82],"speedup":[83,96],"2.09":[85],"over":[86],"CSR":[87],"kernel":[89],"all":[91],"matrices.":[93],"maximum":[95],"go":[98],"up":[99],"3.24.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
