{"id":"https://openalex.org/W2090593986","doi":"https://doi.org/10.1145/2063384.2063431","title":"Fast implementation of DGEMM on Fermi GPU","display_name":"Fast implementation of DGEMM on Fermi GPU","publication_year":2011,"publication_date":"2011-11-08","ids":{"openalex":"https://openalex.org/W2090593986","doi":"https://doi.org/10.1145/2063384.2063431","mag":"2090593986"},"language":"en","primary_location":{"id":"doi:10.1145/2063384.2063431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063431","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":"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/A5104072170","display_name":"Guangming Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["Key Laboratory of Computer Architecture, Institute of Computing Technology","Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer Architecture, Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Science","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070465173","display_name":"Linchuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linchuan Li","raw_affiliation_strings":["Key Laboratory of Computer Architecture, Institute of Computing Technology","Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer Architecture, Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Science","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008655816","display_name":"Sean Triechle","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sean Triechle","raw_affiliation_strings":["Nvidia Corporation","NVIDIA.CORPORATION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia Corporation","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA.CORPORATION","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006141934","display_name":"Everett Phillips","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Everett Phillips","raw_affiliation_strings":["Nvidia Corporation","NVIDIA.CORPORATION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia Corporation","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA.CORPORATION","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101807410","display_name":"Yungang Bao","orcid":"https://orcid.org/0000-0001-6565-5276"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yungang Bao","raw_affiliation_strings":["Key Laboratory of Computer Architecture, Institute of Computing Technology","Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer Architecture, Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Science","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101738014","display_name":"Ninghui Sun","orcid":"https://orcid.org/0000-0002-4179-2660"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ninghui Sun","raw_affiliation_strings":["Key Laboratory of Computer Architecture, Institute of Computing Technology","Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer Architecture, Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Science","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9976000189781189,"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":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.8395984172821045},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7818688154220581},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7676032781600952},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6954018473625183},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4741211235523224},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4437854588031769},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.43806272745132446},{"id":"https://openalex.org/keywords/fermi-gamma-ray-space-telescope","display_name":"Fermi Gamma-ray Space Telescope","score":0.41243380308151245},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40263476967811584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19444039463996887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8395984172821045},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7818688154220581},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7676032781600952},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6954018473625183},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4741211235523224},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4437854588031769},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.43806272745132446},{"id":"https://openalex.org/C186769553","wikidata":"https://www.wikidata.org/wiki/Q726648","display_name":"Fermi Gamma-ray Space Telescope","level":2,"score":0.41243380308151245},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40263476967811584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19444039463996887},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1145/2063384.2063431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063431","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1486858006","display_name":null,"funder_award_id":"2009AA01A129","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G6247896493","display_name":null,"funder_award_id":"2011CB302500","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G6506818310","display_name":null,"funder_award_id":"6.08E+31","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1863336885","https://openalex.org/W1964477602","https://openalex.org/W1992851788","https://openalex.org/W2002257715","https://openalex.org/W2063186542","https://openalex.org/W2071148743","https://openalex.org/W2073061372","https://openalex.org/W2099059741","https://openalex.org/W2110195531","https://openalex.org/W2148542244","https://openalex.org/W2153492376"],"related_works":["https://openalex.org/W2392023973","https://openalex.org/W3038415719","https://openalex.org/W2151444896","https://openalex.org/W2736024852","https://openalex.org/W2186439059","https://openalex.org/W52302056","https://openalex.org/W2057136263","https://openalex.org/W1981557297","https://openalex.org/W2099021415","https://openalex.org/W2090593986"],"abstract_inverted_index":{"In":[0],"this":[1,84],"paper":[2],"we":[3],"present":[4],"a":[5,48],"thorough":[6],"experience":[7],"on":[8,14,52],"tuning":[9],"double-precision":[10],"matrix-matrix":[11],"multiplication":[12],"(DGEM-M)":[13],"the":[15,34,37,76,89,101],"Fermi":[16,38],"GPU":[17],"architecture.":[18],"We":[19,80],"choose":[20],"an":[21,86],"optimal":[22],"algorithm":[23,71],"with":[24,75,85],"blocking":[25],"in":[26,88,97],"both":[27],"shared":[28],"memory":[29,39,63],"and":[30,65],"registers":[31],"to":[32,94,111],"satisfy":[33],"constraints":[35],"of":[36,61],"hierarchy.":[40],"Our":[41,55,68],"optimization":[42],"strategy":[43],"is":[44,106],"further":[45,81],"guided":[46],"by":[47],"performance":[49,74,104],"modeling":[50],"based":[51],"micro-architecture":[53],"benchmarks.":[54],"optimizations":[56],"include":[57],"software":[58],"pipelining,":[59],"use":[60],"vector":[62],"operations,":[64],"instruction":[66],"scheduling.":[67],"best":[69],"CUDA":[70],"achieves":[72],"comparable":[73],"latest":[77],"CUBLAS":[78],"library.":[79],"improve":[82],"upon":[83],"implementation":[87],"native":[90],"machine":[91],"language,":[92],"leading":[93],"20%":[95],"increase":[96],"performance.":[98],"That":[99],"is,":[100],"achieved":[102],"peak":[103],"(efficiency)":[105],"improved":[107],"from":[108],"302Gflop/s":[109],"(58%)":[110],"362Gflop/s":[112],"(70%).":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":16}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}
