{"id":"https://openalex.org/W2096672917","doi":"https://doi.org/10.1109/ipdps.2010.5470394","title":"Implementing the Himeno benchmark with CUDA on GPU clusters","display_name":"Implementing the Himeno benchmark with CUDA on GPU clusters","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2096672917","doi":"https://doi.org/10.1109/ipdps.2010.5470394","mag":"2096672917"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","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/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 H. Phillips","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, CA, USA","NVIDIA Corp, Santa Clara, California, UNITED STATES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA Corp, Santa Clara, California, UNITED STATES","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":false,"raw_author_name":"Massimiliano Fatica","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, CA, USA","NVIDIA Corp, Santa Clara, California, UNITED STATES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA Corp, Santa Clara, California, UNITED STATES","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9994999766349792,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/cuda","display_name":"CUDA","score":0.9284214377403259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8698209524154663},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8508114218711853},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7624411582946777},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7576543092727661},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5861518383026123},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.551323652267456},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5315468311309814},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.42388230562210083},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4128243923187256},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.41175681352615356},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.22650933265686035},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.15625330805778503}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9284214377403259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8698209524154663},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8508114218711853},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7624411582946777},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7576543092727661},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5861518383026123},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.551323652267456},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5315468311309814},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.42388230562210083},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4128243923187256},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.41175681352615356},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22650933265686035},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.15625330805778503},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2010.5470394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2053987390","https://openalex.org/W2101650420"],"related_works":["https://openalex.org/W1997955449","https://openalex.org/W2071296827","https://openalex.org/W2030707850","https://openalex.org/W2012928711","https://openalex.org/W2096672917","https://openalex.org/W2070468128","https://openalex.org/W17610788","https://openalex.org/W4288452443","https://openalex.org/W3142517318","https://openalex.org/W2256606255"],"abstract_inverted_index":{"This":[0],"paper":[1,79],"describes":[2],"the":[3,9,31,81],"use":[4],"of":[5,30,88],"CUDA":[6,54],"to":[7,20,56,84],"accelerate":[8],"Himeno":[10],"benchmark":[11],"on":[12,35,72],"clusters":[13],"with":[14,60,75],"GPUs.":[15,77],"The":[16,78],"implementation":[17,49],"is":[18],"designed":[19],"optimize":[21],"memory":[22],"bandwidth":[23,34],"utilization.":[24],"Our":[25],"approach":[26],"achieves":[27],"over":[28,44,69],"83%":[29],"theoretical":[32],"peak":[33],"a":[36,73],"NVIDIA":[37],"Tesla":[38],"C1060":[39],"GPU":[40,58],"and":[41,66],"performs":[42,67],"at":[43,68],"50":[45],"GFlops.":[46],"A":[47],"multi-GPU":[48],"that":[50],"utilizes":[51],"MPI":[52],"alongside":[53],"streams":[55],"overlap":[57],"execution":[59],"data":[61],"transfers":[62],"allows":[63],"linear":[64],"scaling":[65],"800":[70],"GFlops":[71],"cluster":[74],"16":[76],"presents":[80],"optimizations":[82],"required":[83],"achieve":[85],"this":[86],"level":[87],"performance.":[89]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}