{"id":"https://openalex.org/W2048558763","doi":"https://doi.org/10.1145/2063384.2063392","title":"Optimizing symmetric dense matrix-vector multiplication on GPUs","display_name":"Optimizing symmetric dense matrix-vector multiplication on GPUs","publication_year":2011,"publication_date":"2011-11-08","ids":{"openalex":"https://openalex.org/W2048558763","doi":"https://doi.org/10.1145/2063384.2063392","mag":"2048558763"},"language":"en","primary_location":{"id":"doi:10.1145/2063384.2063392","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","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/A5109721685","display_name":"Rajib Nath","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajib Nath","raw_affiliation_strings":["University of California, San Diego","Computer Science & Engineering, University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Computer Science & Engineering, University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["University of Tennessee, Knoxville","Electrical Engineering and Computer Sciences, University of Tennessee, Knoxville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"Electrical Engineering and Computer Sciences, University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039642335","display_name":"Tingxing Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tingxing \"Tim\" Dong","raw_affiliation_strings":["University of Tennessee, Knoxville","Electrical Engineering and Computer Sciences, University of Tennessee, Knoxville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"Electrical Engineering and Computer Sciences, University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, Knoxville","Electrical Engineering and Computer Sciences, University of Tennessee, Knoxville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"Electrical Engineering and Computer Sciences, University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.956,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.97339838,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9972000122070312,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7766040563583374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6867525577545166},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6310046911239624},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.624854564666748},{"id":"https://openalex.org/keywords/dot-product","display_name":"Dot product","score":0.6034117937088013},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5804122090339661},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5447971224784851},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5382506847381592},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.5211912989616394},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4840475916862488},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4636218845844269},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4525713622570038},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4292837977409363},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4120677709579468},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37248313426971436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17690962553024292},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09004038572311401},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.08314526081085205}],"concepts":[{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7766040563583374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6867525577545166},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6310046911239624},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.624854564666748},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.6034117937088013},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5804122090339661},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5447971224784851},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5382506847381592},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.5211912989616394},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4840475916862488},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4636218845844269},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4525713622570038},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4292837977409363},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4120677709579468},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37248313426971436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17690962553024292},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09004038572311401},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.08314526081085205},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2063384.2063392","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.233.3882","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.233.3882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icl.cs.utk.edu/news_pub/submissions/a6-nath.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.47999998927116394}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W57332520","https://openalex.org/W164329846","https://openalex.org/W1480928214","https://openalex.org/W1596351413","https://openalex.org/W1863336885","https://openalex.org/W1964031104","https://openalex.org/W1972209410","https://openalex.org/W2063186542","https://openalex.org/W2096070062","https://openalex.org/W2099021415","https://openalex.org/W2125960020","https://openalex.org/W2146959317","https://openalex.org/W2148542244","https://openalex.org/W2167647609","https://openalex.org/W2169150754","https://openalex.org/W2506226536","https://openalex.org/W4243796884","https://openalex.org/W6724808235"],"related_works":["https://openalex.org/W1985269159","https://openalex.org/W2999652941","https://openalex.org/W2293771254","https://openalex.org/W2608151934","https://openalex.org/W4288634132","https://openalex.org/W2102729529","https://openalex.org/W4381050447","https://openalex.org/W4311266784","https://openalex.org/W2981978625","https://openalex.org/W2094139070"],"abstract_inverted_index":{"GPUs":[0],"are":[1,140],"excellent":[2],"accelerators":[3],"for":[4,37,73,110,147],"data":[5,10,22],"parallel":[6],"applications":[7],"with":[8,20],"regular":[9],"access":[11,23],"patterns.":[12],"It":[13],"is":[14,30,45,113],"challenging,":[15],"however,":[16],"to":[17,88,94,143],"optimize":[18],"computations":[19],"irregular":[21],"patterns":[24],"on":[25,62,78,101],"GPUs.":[26,79],"One":[27],"such":[28,55],"computation":[29],"the":[31,42,50,75,95,102,132,138,153],"Symmetric":[32],"Matrix":[33],"Vector":[34],"product":[35],"(SYMV)":[36],"dense":[38],"linear":[39,57],"algebra.":[40],"Optimizing":[41],"SYMV":[43,76,82,107],"kernel":[44,77,108],"important":[46],"because":[47],"it":[48],"forms":[49],"basis":[51],"of":[52,145,156],"fundamental":[53],"algorithms":[54],"as":[56],"solvers":[58,61],"and":[59,122,135],"eigenvalue":[60],"symmetric":[63],"matrices.":[64],"In":[65],"this":[66],"work,":[67],"we":[68],"present":[69],"a":[70,89],"new":[71],"algorithm":[72],"optimizing":[74],"Our":[80,106],"optimized":[81],"in":[83,119,128,137],"single":[84,120],"precision":[85,121],"brings":[86],"up":[87,92],"7x":[90],"speed":[91],"compared":[93],"(latest)":[96],"CUBLAS":[97,117,126],"4.0":[98,118,127],"NVIDIA":[99],"library":[100],"GTX":[103],"280":[104],"GPU.":[105],"tuned":[109],"Fermi":[111],"C2050":[112],"4.5x":[114],"faster":[115,124],"than":[116,125],"2x":[123],"double":[129],"precision.":[130],"Moreover,":[131],"techniques":[133],"used":[134],"described":[136],"paper":[139],"general":[141],"enough":[142],"be":[144],"interest":[146],"developing":[148],"high-performance":[149],"GPU":[150],"kernels":[151],"beyond":[152],"particular":[154],"case":[155],"SYMV.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}