{"id":"https://openalex.org/W2182472769","doi":null,"title":"Autotuning GEMMs for Fermi","display_name":"Autotuning GEMMs for Fermi","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2182472769","mag":"2182472769"},"language":"it","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.138","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/lapack/lawnspdf/lawn245.pdf","raw_type":"text"},"volume":null,"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/A5070456582","display_name":"Jakub Kurzak A","orcid":"https://orcid.org/0000-0002-9697-0145","observed_orcids":["https://orcid.org/0000-0002-9697-0145"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakub Kurzak","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9697-0145","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Z. Tomov","orcid":"https://orcid.org/0000-0002-5937-7959","observed_orcids":["https://orcid.org/0000-0002-5937-7959"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5937-7959","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack J. Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782","observed_orcids":["https://orcid.org/0000-0003-3247-1782"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3247-1782","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5691,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9501845,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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":0.001500000013038516,"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":0.00019999999494757503,"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/auto-tuning","display_name":"auto-tuning","score":0.9890000224113464},{"id":"https://openalex.org/keywords/general-matrix-multiplication","display_name":"general matrix multiplication","score":0.8569999933242798},{"id":"https://openalex.org/keywords/gemm","display_name":"GEMM","score":0.7490000128746033},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.7059999704360962},{"id":"https://openalex.org/keywords/dense-matrix-multiplication","display_name":"dense matrix multiplication","score":0.6029999852180481},{"id":"https://openalex.org/keywords/code-generation","display_name":"code generation","score":0.5260000228881836},{"id":"https://openalex.org/keywords/search-space-pruning","display_name":"search space pruning","score":0.8410000205039978},{"id":"https://openalex.org/keywords/performance-benchmarking","display_name":"performance benchmarking","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371669054031372},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6130191683769226},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5992064476013184},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5375338196754456},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4980175495147705},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.49755409359931946},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.49359047412872314},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.47483521699905396},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.45978692173957825},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4585767090320587},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.45855826139450073},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45277339220046997},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.43536272644996643},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4192246198654175},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.416536808013916},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.41068127751350403},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38485661149024963},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.22687813639640808},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19860124588012695},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1624746322631836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11237618327140808},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10445243120193481},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.138","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/lapack/lawnspdf/lawn245.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.637.8052","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.637.8052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/lapack/lawnspdf/lawn245.pdf","raw_type":"text"},{"id":"mag:2182472769","doi":null,"is_oa":false,"landing_page_url":"http://icl.cs.utk.edu/news_pub/submissions/lawn245.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"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":22,"referenced_works":["https://openalex.org/W94439627","https://openalex.org/W1480928214","https://openalex.org/W1547909858","https://openalex.org/W1863336885","https://openalex.org/W1964031104","https://openalex.org/W2016279572","https://openalex.org/W2058178641","https://openalex.org/W2063186542","https://openalex.org/W2071148743","https://openalex.org/W2079658918","https://openalex.org/W2082352135","https://openalex.org/W2085082654","https://openalex.org/W2099021415","https://openalex.org/W2099625934","https://openalex.org/W2102182691","https://openalex.org/W2107911628","https://openalex.org/W2116097016","https://openalex.org/W2125277034","https://openalex.org/W2136952590","https://openalex.org/W2146406121","https://openalex.org/W2146959317","https://openalex.org/W2169631286"],"related_works":["https://openalex.org/W1978642402","https://openalex.org/W2902243168","https://openalex.org/W2914926228","https://openalex.org/W297014570","https://openalex.org/W2100115659","https://openalex.org/W2732908532","https://openalex.org/W7096867518","https://openalex.org/W2090593986","https://openalex.org/W6945258355","https://openalex.org/W1675515972"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,25,28,53,65,74,115,128,132],"use":[4],"of":[5,15,27,56,73,103,109,123],"graphics":[6],"chips":[7],"has":[8],"been":[9],"recognized":[10],"as":[11,40,61],"a":[12,87,96,100,139],"viable":[13],"way":[14],"accelerating":[16],"scientific":[17],"and":[18,45,63,113],"engineering":[19],"ap-plications,":[20],"even":[21],"more":[22,75],"so":[23],"since":[24],"introduction":[26],"Fermi":[29],"architecture":[30],"by":[31],"NVIDIA,":[32],"with":[33,48],"features":[34],"essential":[35],"to":[36,78,138],"numeri-cal":[37],"computing,":[38],"such":[39,60],"fast":[41],"double":[42],"precision":[43],"arithmetic":[44],"memory":[46],"protected":[47],"error":[49],"correction":[50],"codes.":[51],"Being":[52],"crucial":[54],"component":[55],"numerical":[57],"software":[58],"packages,":[59],"LAPACK":[62],"ScaLAPACK,":[64],"general":[66],"dense":[67],"matrix":[68,91],"mul-tiplication":[69],"routine":[70],"is":[71,126],"one":[72],"important":[76],"workloads":[77],"be":[79],"implemented":[80],"on":[81,107],"these":[82],"devices.":[83],"This":[84],"article":[85],"presents":[86],"methodology":[88],"for":[89,95,130],"producing":[90],"multiplication":[92],"kernels":[93],"tuned":[94],"specific":[97],"architecture,":[98],"through":[99,118],"canonical":[101],"process":[102],"heuristic":[104],"autotuning,":[105],"based":[106],"generation":[108],"multiple":[110],"code":[111],"variants":[112],"selecting":[114],"fastest":[116],"ones":[117],"benchmark-ing.":[119],"The":[120],"key":[121],"contribution":[122],"this":[124],"work":[125],"in":[127],"method":[129],"generating":[131],"search":[133],"space;":[134],"specifically,":[135],"pruning":[136],"it":[137],"manageable":[140],"size.":[141],"Performance":[142],"numbers":[143],"match":[144],"or":[145],"exceed":[146],"other":[147],"available":[148],"implementations.":[149]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2016-06-24T00:00:00"}