{"id":"https://openalex.org/W1508286210","doi":"https://doi.org/10.1109/asap.2015.7245713","title":"LightSpMV: Faster CSR-based sparse matrix-vector multiplication on CUDA-enabled GPUs","display_name":"LightSpMV: Faster CSR-based sparse matrix-vector multiplication on CUDA-enabled GPUs","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1508286210","doi":"https://doi.org/10.1109/asap.2015.7245713","mag":"1508286210"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2015.7245713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2015.7245713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 26th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5100617992","display_name":"Yongchao Liu","orcid":"https://orcid.org/0000-0003-3440-9675"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongchao Liu","raw_affiliation_strings":["School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, GA, USA","School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, 30332, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020388832","display_name":"Bertil Schmidt","orcid":"https://orcid.org/0000-0003-2597-8331"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Institut f\u00fcr Informatik Johannes, Gutenberg Universit\u00e4t Mainz, Mainz, Germany","Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, 55128, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Informatik Johannes, Gutenberg Universit\u00e4t Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, 55128, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"82","last_page":"89"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8843928575515747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912418246269226},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7666894197463989},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7123355865478516},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6867441534996033},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6207805871963501},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.46904000639915466},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4510646164417267},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.429848849773407},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.42451009154319763},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.41373205184936523},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34921950101852417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2807806134223938},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.18011441826820374},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.16081532835960388},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10937684774398804},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.09837210178375244}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8843928575515747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912418246269226},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7666894197463989},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7123355865478516},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6867441534996033},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6207805871963501},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.46904000639915466},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4510646164417267},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.429848849773407},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.42451009154319763},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.41373205184936523},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34921950101852417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2807806134223938},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.18011441826820374},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.16081532835960388},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10937684774398804},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.09837210178375244},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2015.7245713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2015.7245713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 26th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W38796834","https://openalex.org/W1506342804","https://openalex.org/W1515144947","https://openalex.org/W1568272005","https://openalex.org/W1588915715","https://openalex.org/W1768849904","https://openalex.org/W1990343439","https://openalex.org/W2023930909","https://openalex.org/W2031460602","https://openalex.org/W2035080386","https://openalex.org/W2063186542","https://openalex.org/W2087507944","https://openalex.org/W2088866486","https://openalex.org/W2095836023","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2518567779","https://openalex.org/W3141650078","https://openalex.org/W4285719527","https://openalex.org/W6601512498","https://openalex.org/W6635140808","https://openalex.org/W6659374036"],"related_works":["https://openalex.org/W52302056","https://openalex.org/W3038415719","https://openalex.org/W2186439059","https://openalex.org/W2011159963","https://openalex.org/W2256144436","https://openalex.org/W1978647314","https://openalex.org/W1981557297","https://openalex.org/W2791204867","https://openalex.org/W1501847821","https://openalex.org/W1481877323"],"abstract_inverted_index":{"Compressed":[0],"sparse":[1,10,17,131],"row":[2,101],"(CSR)":[3],"is":[4,160,193],"a":[5,71,168],"frequently":[6],"used":[7],"format":[8],"for":[9,41,186],"matrix":[11,93],"storage.":[12],"However,":[13],"the":[14,34,77,88,108,121,138,143,154],"state-of-the-art":[15,144],"CSR-based":[16,139],"matrix-vector":[18],"multiplication":[19],"(SpMV)":[20],"implementations":[21],"on":[22,153],"CUDA-enabled":[23],"GPUs":[24],"do":[25],"not":[26],"exhibit":[27],"very":[28],"high":[29,83],"efficiency.":[30],"This":[31],"has":[32],"motivated":[33],"development":[35],"of":[36,92,170],"some":[37],"alternative":[38],"storage":[39,66],"formats":[40],"GPU":[42],"computing.":[43],"Unfortunately,":[44],"these":[45],"alternatives":[46],"are":[47],"incompatible":[48],"with":[49,113,167],"most":[50],"CPU-centric":[51],"programs":[52],"and":[53,65,110,116,133,146,165,174,178,182,188],"require":[54],"dynamic":[55,90,100],"conversion":[56],"from":[57,87],"CSR":[58,79],"at":[59,107,195],"runtime,":[60],"thus":[61],"incurring":[62],"significant":[63],"computational":[64],"overheads.":[67],"We":[68,125],"present":[69],"LightSpMV,":[70,98],"novel":[72],"CUDA-compatible":[73],"SpMV":[74,140],"algorithm":[75],"using":[76,129],"standard":[78],"format,":[80],"which":[81],"achieves":[82],"speed":[84],"by":[85],"benefiting":[86],"fine-grained":[89],"distribution":[91,102],"rows":[94],"over":[95,176,184],"warps/vectors.":[96],"In":[97],"two":[99],"approaches":[103],"have":[104,126],"been":[105],"investigated":[106],"vector":[109],"warp":[111,117],"levels":[112],"atomic":[114],"operations":[115],"shuffle":[118],"functions":[119],"as":[120],"fundamental":[122],"building":[123],"blocks.":[124],"evaluated":[127],"LightSpMV":[128,159,192],"various":[130],"matrices":[132],"further":[134],"compared":[135],"it":[136],"to":[137,162,172,180],"subprograms":[141],"in":[142],"CUSP":[145,164],"cuSPARSE":[147,185],"libraries.":[148],"Performance":[149],"evaluation":[150],"reveals":[151],"that":[152],"same":[155],"Tesla":[156],"K40c":[157],"GPU,":[158],"superior":[161],"both":[163],"cuSPARSE,":[166],"speedup":[169],"up":[171,179],"2.60":[173],"2.63":[175],"CUSP,":[177],"1.93":[181],"1.79":[183],"single":[187],"double":[189],"precision,":[190],"respectively.":[191],"available":[194],"http://lightspmv.sourceforge.net.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}