{"id":"https://openalex.org/W2076165488","doi":"https://doi.org/10.1109/hpcsim.2012.6266964","title":"Accurate CUDA performance modeling for sparse matrix-vector multiplication","display_name":"Accurate CUDA performance modeling for sparse matrix-vector multiplication","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W2076165488","doi":"https://doi.org/10.1109/hpcsim.2012.6266964","mag":"2076165488"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2012.6266964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2012.6266964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on High Performance Computing & Simulation (HPCS)","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/A5020083340","display_name":"Ping Guo","orcid":"https://orcid.org/0000-0002-7122-1084"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Guo","raw_affiliation_strings":["Department of Computer Science, University of Wurzburg, USA","Department of Computer Science, University of Wyoming, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Wurzburg, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, University of Wyoming, USA#TAB#","institution_ids":["https://openalex.org/I12834331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100427875","display_name":"Liqiang Wang","orcid":"https://orcid.org/0000-0002-9832-3056"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liqiang Wang","raw_affiliation_strings":["Department of Computer Science, University of Wurzburg, USA","Department of Computer Science, University of Wyoming, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Wurzburg, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, University of Wyoming, USA#TAB#","institution_ids":["https://openalex.org/I12834331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12834331"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"496","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9866999983787537,"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/cuda","display_name":"CUDA","score":0.9570891857147217},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.8191235661506653},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8061583638191223},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.8045238256454468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6896126866340637},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.49610480666160583},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4316099286079407},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4291284382343292},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.42123302817344666},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.41547727584838867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32213813066482544},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18501776456832886},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0665743350982666},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06291714310646057},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.05723288655281067},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.055354028940200806}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9570891857147217},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.8191235661506653},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8061583638191223},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.8045238256454468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6896126866340637},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.49610480666160583},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4316099286079407},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4291284382343292},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.42123302817344666},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41547727584838867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32213813066482544},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18501776456832886},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0665743350982666},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06291714310646057},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.05723288655281067},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.055354028940200806},{"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/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/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:10.1109/hpcsim.2012.6266964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2012.6266964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.5240","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.5240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uwyo.edu/~lwang7/papers/HPCS-2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"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":21,"referenced_works":["https://openalex.org/W1997573906","https://openalex.org/W2038071684","https://openalex.org/W2103877122","https://openalex.org/W2105545110","https://openalex.org/W2107483876","https://openalex.org/W2113282196","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2130289795","https://openalex.org/W2130336316","https://openalex.org/W2144511445","https://openalex.org/W2148542244","https://openalex.org/W2154118576","https://openalex.org/W2157456954","https://openalex.org/W2167334577","https://openalex.org/W2183317050","https://openalex.org/W2186522450","https://openalex.org/W2997945685","https://openalex.org/W4285719527","https://openalex.org/W6631634815","https://openalex.org/W6681405181"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"integrated":[4],"analytical":[5],"and":[6,27,94,100,110],"profile-based":[7],"CUDA":[8,30],"performance":[9,76],"modeling":[10],"approach":[11],"to":[12],"accurately":[13],"predict":[14],"the":[15,49,57,75,84,89,104,113],"kernel":[16],"execution":[17,50,59],"times":[18,51,60],"of":[19,40,61,71],"sparse":[20],"matrix-vector":[21],"multiplication":[22],"for":[23,68],"CSR,":[24,97],"ELL,":[25,98],"COO,":[26,99],"HYB":[28,101],"SpMV":[29,63,102],"kernels.":[31],"Based":[32],"on":[33,37,45,112],"our":[34,54],"experiments":[35],"conducted":[36],"a":[38],"collection":[39],"8":[41],"widely-used":[42],"testing":[43],"matrices":[44],"NVIDIA":[46],"Tesla":[47],"C2050,":[48],"predicted":[52],"by":[53],"model":[55],"match":[56],"measured":[58],"NVIDIA's":[62],"implementations":[64],"very":[65],"well.":[66],"Specifically,":[67],"29":[69],"out":[70],"32":[72],"test":[73,87],"cases,":[74,88],"differences":[77,90,105],"are":[78,91,106],"under":[79],"or":[80],"around":[81],"7%.":[82],"For":[83,96],"rest":[85],"3":[86],"between":[92],"8%":[93],"10%.":[95],"kernels,":[103],"4.2%,":[107],"5.2%,":[108],"1.0%,":[109],"5.7%":[111],"average,":[114],"respectively.":[115]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}