{"id":"https://openalex.org/W2320652536","doi":"https://doi.org/10.1177/1094342015599239","title":"Performance analysis of the high-performance conjugate gradient benchmark on GPUs","display_name":"Performance analysis of the high-performance conjugate gradient benchmark on GPUs","publication_year":2015,"publication_date":"2015-08-17","ids":{"openalex":"https://openalex.org/W2320652536","doi":"https://doi.org/10.1177/1094342015599239","mag":"2320652536"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015599239","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015599239","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5006141934","display_name":"Everett Phillips","orcid":null},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"Everett Phillips","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079530787","display_name":"Massimiliano Fatica","orcid":"https://orcid.org/0000-0002-5839-1644"},"institutions":[{"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":["US"],"is_corresponding":true,"raw_author_name":"Massimiliano Fatica","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079530787"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":0.323,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.63251329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"30","issue":"1","first_page":"28","last_page":"38"},"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/T10829","display_name":"Interconnection Networks and Systems","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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/graphics-processing-unit","display_name":"Graphics processing unit","score":0.8491119146347046},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8084844350814819},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7973456382751465},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7931988835334778},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7318820357322693},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6865283250808716},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.640347957611084},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5929746031761169},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.5778757333755493},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5540331602096558},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4618161916732788},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.44949033856391907},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4232522249221802},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.21557176113128662},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16334256529808044},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10295382142066956}],"concepts":[{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.8491119146347046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084844350814819},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7973456382751465},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7931988835334778},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7318820357322693},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6865283250808716},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.640347957611084},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5929746031761169},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.5778757333755493},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5540331602096558},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4618161916732788},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.44949033856391907},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4232522249221802},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.21557176113128662},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16334256529808044},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10295382142066956},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342015599239","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015599239","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1252105715","https://openalex.org/W1495954130","https://openalex.org/W1530872699","https://openalex.org/W1586776267","https://openalex.org/W1994182141","https://openalex.org/W1997542937","https://openalex.org/W2029726208","https://openalex.org/W2096672917","https://openalex.org/W2100061495","https://openalex.org/W2435668395","https://openalex.org/W2587647010","https://openalex.org/W2626696598"],"related_works":["https://openalex.org/W2408545863","https://openalex.org/W643179351","https://openalex.org/W2740469715","https://openalex.org/W2905265805","https://openalex.org/W2162805293","https://openalex.org/W2013629274","https://openalex.org/W3169395362","https://openalex.org/W52131579","https://openalex.org/W2166620913","https://openalex.org/W2151982028"],"abstract_inverted_index":{"Graphics":[0],"processing":[1,78,100,124],"unit":[2,79,101],"accelerated":[3,102],"supercomputers":[4,80,103],"have":[5],"proved":[6],"to":[7,14],"be":[8],"very":[9,106],"effective,":[10],"especially":[11],"with":[12,115,126],"regard":[13],"power":[15],"efficiency,":[16],"for":[17,108,136],"accelerating":[18],"compute":[19],"intensive":[20],"applications":[21],"like":[22],"the":[23,28,34,41,75,82,85,92,132],"high-performance":[24,42,66],"Linpack":[25],"used":[26],"in":[27,81],"TOP500":[29],"list.":[30],"This":[31],"paper":[32],"presents":[33],"details":[35],"of":[36,40,111],"a":[37,45],"CUDA":[38],"implementation":[39],"conjugate":[43],"gradient,":[44],"new":[46,138],"proposed":[47],"benchmark":[48],"that":[49,98,122],"better":[50],"represents":[51],"modern":[52],"application":[53],"workloads":[54],"which":[55],"rely":[56],"more":[57],"heavily":[58],"on":[59,74],"memory":[60,129],"system":[61],"and":[62,90],"network":[63],"performance":[64],"than":[65],"Linpack.":[67],"The":[68],"results":[69],"obtained":[70],"at":[71,88,95],"full":[72],"scale":[73],"largest":[76],"graphics":[77,99,123],"world,":[83],"Titan,":[84],"Cray":[86,93],"XK7":[87],"ORNL":[89],"Piz-Daint,":[91],"XC30":[94],"CSCS,":[96],"indicate":[97],"are":[104,131],"also":[105,119],"effective":[107],"this":[109,137],"type":[110],"workload.":[112],"A":[113],"comparison":[114],"other":[116],"architectures":[117],"is":[118],"presented,":[120],"showing":[121],"units,":[125],"their":[127],"high":[128],"bandwidth,":[130],"highest":[133],"performing":[134],"devices":[135],"benchmark.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}