{"id":"https://openalex.org/W2162626314","doi":"https://doi.org/10.1109/mm.2011.66","title":"Multi-GPU DGEMM and High Performance Linpack on Highly Energy-Efficient Clusters","display_name":"Multi-GPU DGEMM and High Performance Linpack on Highly Energy-Efficient Clusters","publication_year":2011,"publication_date":"2011-07-26","ids":{"openalex":"https://openalex.org/W2162626314","doi":"https://doi.org/10.1109/mm.2011.66","mag":"2162626314"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2011.66","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2011.66","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","raw_type":"journal-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/A5007057012","display_name":"D. R\u00f8hr","orcid":"https://orcid.org/0000-0003-4101-0160"},"institutions":[{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Rohr","raw_affiliation_strings":["Frankfurt Institute of Advanced Studies, Goe University, Frankfurt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Frankfurt Institute of Advanced Studies, Goe University, Frankfurt, Germany","institution_ids":["https://openalex.org/I2801628138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061001194","display_name":"M. Bach","orcid":null},"institutions":[{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Bach","raw_affiliation_strings":["Frankfurt Institute of Advanced Studies, Goe University, Frankfurt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Frankfurt Institute of Advanced Studies, Goe University, Frankfurt, Germany","institution_ids":["https://openalex.org/I2801628138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000732240","display_name":"M. Kretz","orcid":"https://orcid.org/0000-0002-0867-243X"},"institutions":[{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Kretz","raw_affiliation_strings":["Frankfurt Institute of Advanced Studies, Goe University, Frankfurt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Frankfurt Institute of Advanced Studies, Goe University, Frankfurt, Germany","institution_ids":["https://openalex.org/I2801628138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053660490","display_name":"V. Lindenstruth","orcid":"https://orcid.org/0009-0006-7301-988X"},"institutions":[{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Lindenstruth","raw_affiliation_strings":["Frankfurt Institute of Advanced Studies, Goe University, Frankfurt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Frankfurt Institute of Advanced Studies, Goe University, Frankfurt, Germany","institution_ids":["https://openalex.org/I2801628138"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801628138"],"apc_list":{"value":2995,"currency":"USD","value_usd":2995},"apc_paid":null,"fwci":2.1157,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89814975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"31","issue":"5","first_page":"18","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9977999925613403,"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":0.9078205823898315},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.701888918876648},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.6889036893844604},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5810683965682983},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5192470550537109},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5030786395072937},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.49286842346191406},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.452862948179245},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.44307512044906616},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4376789331436157},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3571264147758484},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.22912496328353882},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.21684235334396362},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20042410492897034},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19381317496299744},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.19333085417747498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9078205823898315},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.701888918876648},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.6889036893844604},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5810683965682983},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5192470550537109},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5030786395072937},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.49286842346191406},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.452862948179245},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.44307512044906616},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4376789331436157},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3571264147758484},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22912496328353882},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.21684235334396362},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20042410492897034},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19381317496299744},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.19333085417747498},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2011.66","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2011.66","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320881","display_name":"Universit\u00e4t Heidelberg","ror":"https://ror.org/038t36y30"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W133977063","https://openalex.org/W2002257715","https://openalex.org/W2044953540","https://openalex.org/W2083906335","https://openalex.org/W2097309756","https://openalex.org/W2111490460","https://openalex.org/W2165384099","https://openalex.org/W2165831368","https://openalex.org/W4232616815"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"High":[0],"Performance":[1],"Linpack":[2],"can":[3,48],"maximize":[4],"requirements":[5],"throughout":[6],"a":[7,28,44],"computer":[8,30],"system.":[9],"An":[10],"efficient":[11],"multi-GPU":[12],"double-precision":[13],"general":[14],"matrix":[15],"multiply":[16],"(DGEMM),":[17],"together":[18],"with":[19],"adjustments":[20],"to":[21,26,31],"the":[22,38],"HPL,":[23],"is":[24],"required":[25],"utilize":[27,49],"heterogeneous":[29],"its":[32],"full":[33],"extent.":[34],"The":[35],"authors":[36],"present":[37],"resulting":[39],"energy-efficiency":[40],"measurements":[41],"and":[42],"suggest":[43],"cluster":[45],"design":[46],"that":[47],"multiple":[50],"GPUs.":[51]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
