{"id":"https://openalex.org/W3141650078","doi":"https://doi.org/10.1109/sc.2008.5214359","title":"Benchmarking GPUs to tune dense linear algebra","display_name":"Benchmarking GPUs to tune dense linear algebra","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W3141650078","doi":"https://doi.org/10.1109/sc.2008.5214359","mag":"3141650078"},"language":"en","primary_location":{"id":"doi:10.1109/sc.2008.5214359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2008.5214359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 SC - 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/A5003269014","display_name":"\u0412. \u041c. \u0412\u043e\u043b\u043a\u043e\u0432","orcid":"https://orcid.org/0000-0003-0350-4186"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"V. Volkov","raw_affiliation_strings":["Computer Science Division, University of California Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Division, University of California Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091434158","display_name":"J. Demmel","orcid":"https://orcid.org/0000-0002-0550-5476"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.W. Demmel","raw_affiliation_strings":["Computer Science Division and Department of Mathematics, University of California Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Division and Department of Mathematics, University of California Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003269014"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":49.7306,"has_fulltext":false,"cited_by_count":474,"citation_normalized_percentile":{"value":0.99886681,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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":0.9986000061035156,"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":0.9966999888420105,"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/parallel-computing","display_name":"Parallel computing","score":0.8425686359405518},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8193542957305908},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.7209516763687134},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5903300046920776},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.5754209756851196},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5131223797798157},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5129684805870056},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.44984811544418335},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4167044162750244},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3243996500968933},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08728992938995361}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8425686359405518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193542957305908},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7209516763687134},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5903300046920776},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.5754209756851196},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5131223797798157},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5129684805870056},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.44984811544418335},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4167044162750244},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3243996500968933},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08728992938995361},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sc.2008.5214359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2008.5214359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1505753777","https://openalex.org/W1568272005","https://openalex.org/W1992851788","https://openalex.org/W2002257715","https://openalex.org/W2083056254","https://openalex.org/W2108792719","https://openalex.org/W2122817518","https://openalex.org/W2136834900","https://openalex.org/W2139774022","https://openalex.org/W4230289604","https://openalex.org/W6633966643"],"related_works":["https://openalex.org/W988231918","https://openalex.org/W2087421046","https://openalex.org/W2002833390","https://openalex.org/W2108540054","https://openalex.org/W3023536296","https://openalex.org/W2529540995","https://openalex.org/W2187691968","https://openalex.org/W2025829250","https://openalex.org/W2063186542","https://openalex.org/W3141650078"],"abstract_inverted_index":{"We":[0,76,89,127],"present":[1,128],"performance":[2],"results":[3,61],"for":[4],"dense":[5],"linear":[6],"algebra":[7],"using":[8],"recent":[9],"NVIDIA":[10],"GPUs.":[11],"Our":[12,33,48],"matrix-matrix":[13],"multiply":[14],"routine":[15],"(GEMM)":[16],"runs":[17],"up":[18,40,56],"to":[19,41,57,93],"60%":[20],"faster":[21],"than":[22],"the":[23,28,44,66,70,99,114,141],"vendor's":[24],"implementation":[25],"and":[26,36,73,96,106,121,125,138],"approaches":[27],"peak":[29,45],"of":[30,43,69,98,113,123,131],"hardware":[31],"capabilities.":[32],"LU,":[34],"QR":[35],"Cholesky":[37],"factorizations":[38],"achieve":[39],"80-90%":[42],"GEMM":[46],"rate.":[47],"parallel":[49],"LU":[50],"running":[51],"on":[52,104],"two":[53],"GPUs":[54,80],"achieves":[55],"~540":[58],"Gflop/s.":[59],"These":[60],"are":[62],"accomplished":[63],"by":[64,101],"challenging":[65],"accepted":[67],"view":[68],"GPU":[71,105,115],"architecture":[72],"programming":[74],"guidelines.":[75],"argue":[77],"that":[78,118,143],"modern":[79],"should":[81],"be":[82],"viewed":[83],"as":[84],"multithreaded":[85],"multicore":[86],"vector":[87,94],"units.":[88],"exploit":[90],"blocking":[91],"similarly":[92],"computers":[95],"heterogeneity":[97],"system":[100,117],"computing":[102],"both":[103],"CPU.":[107],"This":[108],"study":[109],"includes":[110],"detailed":[111],"benchmarking":[112],"memory":[116],"reveals":[119],"sizes":[120],"latencies":[122],"caches":[124],"TLB.":[126],"a":[129],"couple":[130],"algorithmic":[132],"optimizations":[133],"aimed":[134],"at":[135],"increasing":[136],"parallelism":[137],"regularity":[139],"in":[140],"problem":[142],"provide":[144],"us":[145],"with":[146],"slightly":[147],"higher":[148],"performance.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":30},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":37},{"year":2013,"cited_by_count":46},{"year":2012,"cited_by_count":62}],"updated_date":"2026-04-22T08:38:42.863108","created_date":"2025-10-10T00:00:00"}