{"id":"https://openalex.org/W3130024571","doi":"https://doi.org/10.1145/3437801.3441592","title":"Efficiently running SpMV on long vector architectures","display_name":"Efficiently running SpMV on long vector architectures","publication_year":2021,"publication_date":"2021-02-17","ids":{"openalex":"https://openalex.org/W3130024571","doi":"https://doi.org/10.1145/3437801.3441592","mag":"3130024571"},"language":"en","primary_location":{"id":"doi:10.1145/3437801.3441592","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437801.3441592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/349246","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052630663","display_name":"Constantino G\u00f3mez","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Constantino G\u00f3mez","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046459017","display_name":"Filippo Mantovani","orcid":"https://orcid.org/0000-0003-3559-4825"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Filippo Mantovani","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004513697","display_name":"Erich Focht","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164122","display_name":"NEC (Germany)","ror":"https://ror.org/05hxss661","country_code":"DE","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210164122"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erich Focht","raw_affiliation_strings":["NEC Deutschland GmbH, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"NEC Deutschland GmbH, Stuttgart, Germany","institution_ids":["https://openalex.org/I4210164122"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044183257","display_name":"Marc Casas","orcid":"https://orcid.org/0000-0003-4564-2093"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marc Casas","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052630663"],"corresponding_institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":7.5458,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.98160638,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"292","last_page":"303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9986000061035156,"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":0.8461301326751709},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8325806856155396},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8034019470214844},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5546784996986389},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.5492081046104431},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4520938992500305},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4468209445476532},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4340292811393738},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4264487326145172},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08643803000450134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461301326751709},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8325806856155396},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8034019470214844},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5546784996986389},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.5492081046104431},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4520938992500305},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4468209445476532},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4340292811393738},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4264487326145172},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08643803000450134},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3437801.3441592","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437801.3441592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/349246","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/349246","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/349246","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/349246","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G5765248861","display_name":null,"funder_award_id":"RYC-2017-23269","funder_id":"https://openalex.org/F4320326262","funder_display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a"},{"id":"https://openalex.org/G6006988010","display_name":null,"funder_award_id":"PID2019-107255GB","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G6456004180","display_name":null,"funder_award_id":"2017-SGR-1414","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"}],"funders":[{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320326262","display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a","ror":"https://ror.org/03sv46s19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W168866822","https://openalex.org/W1588915715","https://openalex.org/W1987840949","https://openalex.org/W2009654791","https://openalex.org/W2101511474","https://openalex.org/W2142820603","https://openalex.org/W2259574154","https://openalex.org/W2415007423","https://openalex.org/W2518567779","https://openalex.org/W2613264175","https://openalex.org/W2730999914","https://openalex.org/W2802808949","https://openalex.org/W2810130280","https://openalex.org/W2902045097","https://openalex.org/W2940194197","https://openalex.org/W3123542955","https://openalex.org/W4316084067"],"related_works":["https://openalex.org/W32529763","https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W2090268225","https://openalex.org/W2366442643","https://openalex.org/W2021715972","https://openalex.org/W2761732860"],"abstract_inverted_index":{"Sparse":[0],"Matrix-Vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4],"an":[5,97],"essential":[6],"kernel":[7],"for":[8,78],"parallel":[9],"numerical":[10],"applications.":[11],"SpMV":[12,26,55],"displays":[13],"sparse":[14,70],"and":[15],"irregular":[16],"data":[17],"accesses,":[18],"which":[19],"complicate":[20],"its":[21],"vectorization.":[22],"Such":[23],"difficulties":[24],"make":[25],"to":[27,51],"frequently":[28],"experiment":[29],"non-optimal":[30],"results":[31],"when":[32],"run":[33],"on":[34,57],"long":[35,59,83,115],"vector":[36,60,84,116],"ISAs":[37],"exploiting":[38],"SIMD":[39,125],"parallelism.":[40,126],"In":[41,62],"this":[42,63],"context,":[43],"the":[44,67,87],"development":[45],"of":[46,107,124],"new":[47,76],"optimizations":[48,77,111],"becomes":[49],"fundamental":[50],"enable":[52],"high":[53,122],"performance":[54,113],"executions":[56],"emerging":[58],"architectures.":[61],"paper,":[64],"we":[65,95],"improve":[66],"state-of-the-art":[68],"SELL-C-\u03c3":[69,102],"matrix":[71],"format":[72],"by":[73],"proposing":[74],"several":[75,93],"SpMV.":[79],"We":[80],"target":[81],"aggressive":[82],"architectures":[85,117],"like":[86],"NEC":[88],"Vector":[89],"Engine.":[90],"By":[91],"combining":[92],"optimizations,":[94],"obtain":[96],"average":[98],"12%":[99],"improvement":[100],"over":[101],"considering":[103],"a":[104,121],"heterogeneous":[105],"set":[106],"24":[108],"matrices.":[109],"Our":[110],"boost":[112],"in":[114],"since":[118],"they":[119],"expose":[120],"degree":[123]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2021-03-01T00:00:00"}
