{"id":"https://openalex.org/W4381389674","doi":"https://doi.org/10.1145/3587828.3587834","title":"GPU Sparse Matrix Vector Multiplication Optimization Based on ELLB Storage Format","display_name":"GPU Sparse Matrix Vector Multiplication Optimization Based on ELLB Storage Format","publication_year":2023,"publication_date":"2023-02-23","ids":{"openalex":"https://openalex.org/W4381389674","doi":"https://doi.org/10.1145/3587828.3587834"},"language":"en","primary_location":{"id":"doi:10.1145/3587828.3587834","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3587828.3587834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3587828.3587834?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3587828.3587834?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085393204","display_name":"Haonan Chen","orcid":"https://orcid.org/0009-0000-0999-9429"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haonan Chen","raw_affiliation_strings":["Guangdong University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0000-0999-9429","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007409112","display_name":"Zhuowei Wang","orcid":"https://orcid.org/0000-0001-6479-5154"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuowei Wang","raw_affiliation_strings":["Guangdong University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-6479-5154","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032362514","display_name":"Lianglun Cheng","orcid":"https://orcid.org/0000-0002-8213-041X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianglun Cheng","raw_affiliation_strings":["Guangdong University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-8213-041X","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085393204"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07299604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"75","issue":null,"first_page":"34","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.998199999332428,"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":0.7585444450378418},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7504213452339172},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.664790689945221},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6423772573471069},{"id":"https://openalex.org/keywords/storage-efficiency","display_name":"Storage efficiency","score":0.5941352844238281},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5858792662620544},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5452069640159607},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.41607287526130676},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.41279321908950806},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3575754165649414},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2925248444080353},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.144452303647995},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08805125951766968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585444450378418},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7504213452339172},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.664790689945221},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6423772573471069},{"id":"https://openalex.org/C121838778","wikidata":"https://www.wikidata.org/wiki/Q7619924","display_name":"Storage efficiency","level":2,"score":0.5941352844238281},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5858792662620544},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5452069640159607},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41607287526130676},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.41279321908950806},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3575754165649414},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2925248444080353},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.144452303647995},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08805125951766968},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":1,"locations":[{"id":"doi:10.1145/3587828.3587834","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3587828.3587834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3587828.3587834?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3587828.3587834","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3587828.3587834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3587828.3587834?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381389674.pdf","grobid_xml":"https://content.openalex.org/works/W4381389674.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2009654791","https://openalex.org/W2035080386","https://openalex.org/W2128853364","https://openalex.org/W2273809747","https://openalex.org/W2557392929","https://openalex.org/W2568669383","https://openalex.org/W2741503025","https://openalex.org/W2766501636","https://openalex.org/W2891818448","https://openalex.org/W2922451881"],"related_works":["https://openalex.org/W2158302790","https://openalex.org/W4321636545","https://openalex.org/W2023476765","https://openalex.org/W4327907098","https://openalex.org/W2387719413","https://openalex.org/W4381389674","https://openalex.org/W2348283597","https://openalex.org/W4256621180","https://openalex.org/W4380875404","https://openalex.org/W2365958426"],"abstract_inverted_index":{"ELLPACK(ELL)":[0],"sparse":[1,16,32,102],"matrix":[2,17,33,48,103],"storage":[3,10,34,41,77,104],"format":[4,44,78,105],"has":[5],"problems":[6],"such":[7],"as":[8],"high":[9],"consumption":[11],"and":[12,62,112],"low":[13],"efficiency":[14,69,115,146],"of":[15,56,70,108,116,143,152],"vector":[18],"multiplication(SpMV).":[19],"To":[20],"solve":[21,80],"this":[22,43],"problem,":[23],"we":[24],"propose":[25],"a":[26],"Graphic":[27],"Processing":[28],"Unit(GPU)-based":[29],"efficient":[30],"ELLPACK-Block(ELLB)":[31],"format.":[35],"Based":[36],"on":[37],"the":[38,47,53,68,75,81,94,100,109,113,126,132,141],"original":[39],"ELL":[40],"format,":[42,99,131],"adaptively":[45],"divides":[46],"into":[49],"blocks":[50],"according":[51],"to":[52,66,79],"average":[54,114,151],"number":[55],"non-zero":[57],"elements":[58],"in":[59],"each":[60],"row,":[61],"uses":[63],"auxiliary":[64],"matrices":[65],"improve":[67],"SpMV":[71,82,118,144],"solution.":[72],"We":[73],"use":[74],"ELLB":[76,101],"problem":[83],"for":[84],"different":[85],"matrices.":[86],"The":[87,145],"experimental":[88],"results":[89],"show":[90],"that":[91],"compared":[92,124],"with":[93,125],"Perfect":[95],"Compressed":[96,128],"Sparse":[97,129],"Row(PCSR)":[98],"saves":[106],"50":[107],"memory":[110,133],"space,":[111],"solving":[117],"is":[119,136,147],"increased":[120,137,148],"by":[121,138,149],"7":[122],"times;":[123],"Effective":[127],"Row(ECSR)":[130],"space":[134],"usage":[135],"25,":[139],"but":[140],"solution":[142],"an":[150],"7.65":[153],"times.":[154]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}