{"id":"https://openalex.org/W7116437847","doi":"https://doi.org/10.1145/3754598.3754632","title":"OVERT: Orchestrating Vector-Scalar Execution for Efficient SpMV on Modern CPUs","display_name":"OVERT: Orchestrating Vector-Scalar Execution for Efficient SpMV on Modern CPUs","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116437847","doi":"https://doi.org/10.1145/3754598.3754632"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754632","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754632","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3754598.3754632","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044386170","display_name":"Kelun Lei","orcid":"https://orcid.org/0000-0001-8637-4182"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kelun Lei","raw_affiliation_strings":["Beihang University, Bejing, China"],"raw_orcid":"https://orcid.org/0000-0001-8637-4182","affiliations":[{"raw_affiliation_string":"Beihang University, Bejing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120892615","display_name":"Hailong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yang","raw_affiliation_strings":["Beihang University, Bejing, China"],"raw_orcid":"https://orcid.org/0000-0003-1101-7927","affiliations":[{"raw_affiliation_string":"Beihang University, Bejing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052897340","display_name":"Kaige Zhang","orcid":"https://orcid.org/0009-0000-3261-3483"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaige Zhang","raw_affiliation_strings":["Beihang University, Bejing, China"],"raw_orcid":"https://orcid.org/0009-0000-3261-3483","affiliations":[{"raw_affiliation_string":"Beihang University, Bejing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111154302","display_name":"Shaokang Du","orcid":"https://orcid.org/0009-0004-0540-0959"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaokang Du","raw_affiliation_strings":["Beihang University, Bejing, China"],"raw_orcid":"https://orcid.org/0009-0004-0540-0959","affiliations":[{"raw_affiliation_string":"Beihang University, Bejing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","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"],"raw_orcid":"https://orcid.org/0000-0003-4564-2093","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/A5120935885","display_name":"Yufan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufan Xu","raw_affiliation_strings":["Independent Researcher, Cupertino, USA"],"raw_orcid":"https://orcid.org/0000-0002-7787-6460","affiliations":[{"raw_affiliation_string":"Independent Researcher, Cupertino, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120891728","display_name":"Zhongzhi Luan","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhi Luan","raw_affiliation_strings":["Beihang University, Bejing, China"],"raw_orcid":"https://orcid.org/0000-0002-7186-0556","affiliations":[{"raw_affiliation_string":"Beihang University, Bejing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1829-2817"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Beihang University, Bejing, China"],"raw_orcid":"https://orcid.org/0000-0003-1829-2817","affiliations":[{"raw_affiliation_string":"Beihang University, Bejing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004400713","display_name":"Depei Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depei Qian","raw_affiliation_strings":["Beihang University, Bejing, China"],"raw_orcid":"https://orcid.org/0000-0002-5382-1473","affiliations":[{"raw_affiliation_string":"Beihang University, Bejing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"564","last_page":"574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8632000088691711,"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":0.8632000088691711,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.0340999998152256,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.021800000220537186,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8555999994277954},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.8446999788284302},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5393999814987183},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.44440001249313354},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.42649999260902405},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41019999980926514},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4099999964237213},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.40139999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8677999973297119},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8555999994277954},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.8446999788284302},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7394000291824341},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5393999814987183},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C171182647","wikidata":"https://www.wikidata.org/wiki/Q126736","display_name":"Scalar multiplication","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.2655999958515167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754632","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754632","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3754598.3754632","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754632","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.4466262757778168,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2732425316","display_name":null,"funder_award_id":"JKF-20240598, JKF-2025012343648","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6139273093","display_name":null,"funder_award_id":"62322201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1525132831","https://openalex.org/W1783256592","https://openalex.org/W1990832096","https://openalex.org/W2009654791","https://openalex.org/W2035080386","https://openalex.org/W2096544401","https://openalex.org/W2101511474","https://openalex.org/W2590246587","https://openalex.org/W2732588537","https://openalex.org/W2751387202","https://openalex.org/W2781752755","https://openalex.org/W2791012218","https://openalex.org/W2891832717","https://openalex.org/W2964357930","https://openalex.org/W2982464808","https://openalex.org/W3175189837","https://openalex.org/W3213457265","https://openalex.org/W4238995617","https://openalex.org/W4247828381","https://openalex.org/W4290648346","https://openalex.org/W4321466355","https://openalex.org/W4321636675","https://openalex.org/W4379537250","https://openalex.org/W4388661983","https://openalex.org/W4392266035","https://openalex.org/W4400409889","https://openalex.org/W4401408710","https://openalex.org/W4405756444","https://openalex.org/W4407857386"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"Matrix-Vector":[1],"Multiplication":[2],"(SpMV)":[3],"is":[4,15],"a":[5,67],"key":[6],"operation":[7],"in":[8],"many":[9],"applications,":[10],"and":[11,79,96,114,162],"optimizing":[12],"its":[13],"performance":[14,27,38],"crucial":[16],"for":[17,54,86],"achieving":[18],"high":[19],"computational":[20],"efficiency.":[21],"Existing":[22],"efforts":[23],"have":[24],"optimized":[25],"SpMV":[26,41,88],"on":[28,45,83,144,159,171],"CPUs":[29,85],"with":[30],"corresponding":[31],"sparse":[32,72],"matrix":[33,73,104],"formats":[34,100],"adopted.":[35],"However,":[36],"the":[37,52,103,128,136,139],"of":[39,71,138,153,166],"existing":[40,99],"implementations":[42],"primarily":[43],"focuses":[44],"maximizing":[46],"hardware\u2019s":[47],"vector":[48,78,113],"unit":[49],"usage,":[50],"neglecting":[51],"potential":[53],"exploiting":[55],"idle":[56],"scalar":[57,80,115],"units":[58,82],"simultaneously.":[59],"To":[60],"address":[61],"such":[62],"limitation,":[63],"we":[64,118],"propose":[65,119],"OVERT,":[66,90],"new":[68],"storage":[69],"format":[70,93,122,130],"designed":[74],"to":[75,135],"exploit":[76],"both":[77],"execution":[81],"modern":[84],"accelerating":[87],"performance.":[89],"containing":[91],"two":[92],"variants":[94],"(OVERT-S":[95],"OVERT-E),":[97],"outperforms":[98],"by":[101],"partitioning":[102],"into":[105],"multiple":[106],"data":[107],"panels,":[108],"which":[109],"can":[110],"efficiently":[111],"utilize":[112],"units.":[116],"Moreover,":[117],"an":[120,150,163],"effective":[121],"selection":[123],"model":[124],"that":[125,147],"dynamically":[126],"chooses":[127],"optimal":[129],"variant":[131],"from":[132],"OVERT":[133,148],"according":[134],"characteristics":[137],"input":[140],"matrix.":[141],"Experimental":[142],"results":[143],"SuiteSparse":[145],"show":[146],"achieves":[149],"average":[151,164],"speedup":[152,165],"3.91":[154],"\u00d7":[155,168],"against":[156,169],"Intel":[157],"MKL":[158],"X86":[160],"CPU":[161],"1.24":[167],"ArmPL":[170],"ARM":[172],"CPU.":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-21T00:00:00"}