{"id":"https://openalex.org/W2386685757","doi":null,"title":"Optimizing Sparse Matrix-vector Multiplication Based on GPU","display_name":"Optimizing Sparse Matrix-vector Multiplication Based on GPU","alternate_titles":[],"publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2386685757","mag":"2386685757"},"language":"en","primary_location":{"id":"mag:2386685757","doi":null,"is_oa":false,"landing_page_url":"https://oversea.cnki.net/kcms/detail/detail.aspx?dbcode=CJFD&filename=JSJA201008038","pdf_url":null,"source":{"id":"https://openalex.org/S4306515071","display_name":"Jisuanji Kexue","issn_l":"1002-137X","issn":["1002-137X"],"is_oa":false,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Computer Science","raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W2386685757"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101574831","display_name":"Lili He","orcid":"https://orcid.org/0000-0002-5279-9016","observed_orcids":["https://orcid.org/0000-0002-5279-9016"]},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"Lili He","raw_affiliation_strings":["College of Computer Science and Technology, jilin University, Changchun 130012, China )"],"raw_orcid":"https://orcid.org/0000-0002-5279-9016","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, jilin University, Changchun 130012, China )","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101574831"],"corresponding_institution_ids":["https://openalex.org/I194450716"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.0008999999845400453,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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-vector-multiplication","display_name":"sparse matrix-vector multiplication","score":1.0},{"id":"https://openalex.org/keywords/gpu-parallel-computing","display_name":"GPU parallel computing","score":0.7789999842643738},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.968999981880188},{"id":"https://openalex.org/keywords/compressed-sparse-row","display_name":"compressed sparse row format","score":0.8100000023841858},{"id":"https://openalex.org/keywords/thread-mapping","display_name":"thread mapping","score":0.8669999837875366},{"id":"https://openalex.org/keywords/memory-coalescing","display_name":"memory coalescing","score":0.8100000023841858},{"id":"https://openalex.org/keywords/texture-memory","display_name":"texture memory","score":0.8510000109672546},{"id":"https://openalex.org/keywords/shared-memory","display_name":"shared memory","score":0.9620000123977661},{"id":"https://openalex.org/keywords/performance-optimization","display_name":"performance optimization","score":0.49000000953674316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9056352376937866},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8254284858703613},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7471252679824829},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.6950638294219971},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.588272750377655},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.539059042930603},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5189856886863708},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.48266270756721497},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.45614951848983765},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.42618328332901},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3643531799316406},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08090662956237793},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2386685757","doi":null,"is_oa":false,"landing_page_url":"https://oversea.cnki.net/kcms/detail/detail.aspx?dbcode=CJFD&filename=JSJA201008038","pdf_url":null,"source":{"id":"https://openalex.org/S4306515071","display_name":"Jisuanji Kexue","issn_l":"1002-137X","issn":["1002-137X"],"is_oa":false,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Computer Science","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W216602197","https://openalex.org/W2527991513","https://openalex.org/W2352892006","https://openalex.org/W2102994616","https://openalex.org/W2617403939","https://openalex.org/W1989568755","https://openalex.org/W2977805805","https://openalex.org/W2124007994","https://openalex.org/W7097885352","https://openalex.org/W2318592257"],"abstract_inverted_index":{"Sparse":[0,26],"matrix":[1],"computations":[2],"present":[3],"additional":[4],"challenges":[5],"for":[6],"harnessing":[7],"the":[8,77],"potential":[9],"of":[10,79,84,114,123],"modern":[11],"graphics":[12],"processing":[13],"unit(GPU)for":[14],"general-purpose":[15],"computing.We":[16],"investigated":[17],"various":[18],"optimizations":[19,41],"on":[20],"thread-mapping,data":[21],"reuse":[22,60],"etc.and":[23],"a":[24,124],"parallel":[25,86],"Matrix-Vector":[27],"multiplication(SpMV)on":[28],"GPU":[29],"with":[30,82],"compute":[31],"unified":[32],"device":[33],"architecture(CUDA)was":[34],"proposed":[35],"under":[36],"compressed":[37],"sparse":[38],"row(CSR)structure":[39],"afterwards.The":[40],"include:(1)exploiting":[42],"each":[43],"element":[44],"using":[45,69],"half-warp":[46],"threads,which":[47],"synchronize":[48],"free":[49],"within":[50],"one":[51,91,97],"warp;(2)making":[52],"up":[53],"integer":[54],"address":[55],"to":[56],"achieve":[57],"coalesced":[58],"accesses;(3)data":[59],"through":[61],"reading":[62],"from":[63,92,98],"texture":[64],"vector":[65],"resides":[66],"in;(4)data":[67],"transfer":[68],"pagelocked":[70],"memory;(5)reading":[71],"results":[72],"in":[73,106],"shared":[74],"memory.We":[75],"compared":[76],"performance":[78,113],"our":[80,115],"approach":[81,102,116],"that":[83,122],"efficient":[85],"SpMV":[87,100],"implementations":[88],"such":[89],"as(1)the":[90],"NVIDIA's":[93,99],"CUDPP":[94],"library":[95],"and(2)the":[96],"library.Our":[101],"outperforms":[103],"two":[104],"both":[105],"memory":[107],"bandwidth":[108],"and":[109],"GFLOPS.In":[110],"addition,the":[111],"total":[112],"is":[117],"three":[118],"times":[119],"greater":[120],"than":[121],"CPU":[125],"counterpart.":[126]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2386685757","counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
