{"id":"https://openalex.org/W40887843","doi":null,"title":"Cache and bandwidth aware matrix multiplication on the GPU","display_name":"Cache and bandwidth aware matrix multiplication on the GPU","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W40887843","mag":"40887843"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.8423","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.8423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/%7Esuvenkat/700/lectures/7/UIUCDCS-R-2003-2328-1.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/A5048125151","display_name":"Jesse D. Hall","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jesse D. Hall","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052779906","display_name":"Nathan Carr","orcid":"https://orcid.org/0000-0003-2324-6428","observed_orcids":["https://orcid.org/0000-0003-2324-6428"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathan Carr","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2324-6428","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111373264","display_name":"John C. Hart","orcid":"https://orcid.org/0000-0002-7102-0055","observed_orcids":["https://orcid.org/0000-0002-7102-0055"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John C. Hart","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7102-0055","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9534,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.9778697,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":98},"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":0.9980000257492065,"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":0.9980000257492065,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.000699999975040555,"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"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.0006000000284984708,"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/matrix-multiplication","display_name":"matrix multiplication","score":0.9340000152587891},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.9259999990463257},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"memory bandwidth","score":0.8109999895095825},{"id":"https://openalex.org/keywords/cache-efficiency","display_name":"cache efficiency","score":0.6690000295639038},{"id":"https://openalex.org/keywords/parallel-algorithms","display_name":"parallel algorithms","score":0.6389999985694885},{"id":"https://openalex.org/keywords/graphics-hardware","display_name":"graphics hardware","score":0.5809999704360962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8388313055038452},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.68604576587677},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6768159866333008},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6424405574798584},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5575963854789734},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5108432173728943},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5085984468460083},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4948124289512634},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4817545413970947},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.44322195649147034},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.430698424577713},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3250791132450104},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32400915026664734},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.8423","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.8423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/%7Esuvenkat/700/lectures/7/UIUCDCS-R-2003-2328-1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.6.5538","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.6.5538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://graphics.cs.uiuc.edu/~jch/papers/UIUCDCS-R-2003-2328.pdf","raw_type":"text"},{"id":"mag:40887843","doi":null,"is_oa":false,"landing_page_url":"https://hgpu.org/?p=945","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":5,"referenced_works":["https://openalex.org/W1485294004","https://openalex.org/W1964031104","https://openalex.org/W2117236520","https://openalex.org/W2127091535","https://openalex.org/W2155009756"],"related_works":["https://openalex.org/W3013519975","https://openalex.org/W2418039659","https://openalex.org/W2007115486","https://openalex.org/W2365142522","https://openalex.org/W2127091535","https://openalex.org/W3032811235","https://openalex.org/W122736772","https://openalex.org/W7098365041","https://openalex.org/W7097732514","https://openalex.org/W2611954624"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,53],"the":[3,21,31,34,63,79,95],"speed":[4],"and":[5,26,98],"programmability":[6],"of":[7,16,23,33,68,81,94,100],"consumer":[8],"level":[9],"graphics":[10],"hardware":[11],"has":[12],"sparked":[13],"a":[14,40],"flurry":[15],"research":[17],"that":[18,77],"goes":[19],"beyond":[20],"realm":[22],"image":[24],"synthesis":[25],"computer":[27],"graphics.":[28],"We":[29],"examine":[30],"use":[32],"GPU":[35,54,64,87,102],"(graphics":[36],"processing":[37],"unit)":[38],"as":[39],"tool":[41],"for":[42,48,59],"scientific":[43],"computing,":[44],"by":[45],"analyzing":[46],"techniques":[47],"performing":[49],"large":[50,82],"matrix":[51,83],"multiplies":[52],"hardware.":[55],"An":[56],"earlier":[57],"method":[58],"multiplying":[60],"matrices":[61],"on":[62,85],"suffered":[65],"from":[66],"problems":[67],"memory":[69,96],"bandwidth.":[70],"This":[71],"paper":[72],"examines":[73],"more":[74,89],"efficient":[75],"algorithms":[76],"make":[78],"implementation":[80],"multiplication":[84],"upcoming":[86],"architectures":[88],"competitive,":[90],"using":[91],"only":[92],"25%":[93],"bandwidth":[97],"instructions":[99],"previous":[101],"algorithms.":[103]},"counts_by_year":[{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}