{"id":"https://openalex.org/W2122002474","doi":"https://doi.org/10.1109/icpp.2011.71","title":"Parallel Performance Measurement of Heterogeneous Parallel Systems with GPUs","display_name":"Parallel Performance Measurement of Heterogeneous Parallel Systems with GPUs","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W2122002474","doi":"https://doi.org/10.1109/icpp.2011.71","mag":"2122002474"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpp.2011.71","pdf_url":null,"source":{"id":"https://openalex.org/S4306424025","display_name":"International Conference on Parallel Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5029524538","display_name":"Allen D. Malony","orcid":"https://orcid.org/0000-0002-9598-7201"},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allen D. Malony","raw_affiliation_strings":["Dept of Computer and Information Science, University of Oregon, Eugene, OR, USA"],"affiliations":[{"raw_affiliation_string":"Dept of Computer and Information Science, University of Oregon, Eugene, OR, USA","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105669996","display_name":"Scott Biersdorff","orcid":"https://orcid.org/0000-0003-4210-7335"},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Biersdorff","raw_affiliation_strings":["Dept of Computer and Information Science, University of Oregon, Eugene, OR, USA"],"affiliations":[{"raw_affiliation_string":"Dept of Computer and Information Science, University of Oregon, Eugene, OR, USA","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240094","display_name":"Sameer Shende","orcid":"https://orcid.org/0000-0002-2592-669X"},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sameer Shende","raw_affiliation_strings":["Dept of Computer and Information Science, University of Oregon, Eugene, OR, USA"],"affiliations":[{"raw_affiliation_string":"Dept of Computer and Information Science, University of Oregon, Eugene, OR, USA","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050514538","display_name":"Heike Jagode","orcid":"https://orcid.org/0000-0002-8173-9434"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heike Jagode","raw_affiliation_strings":["Innovative Comput. Lab. (ICL), Univ. of Tennessee, Knoxville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Innovative Comput. Lab. (ICL), Univ. of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["Innovative Comput. Lab. (ICL), Univ. of Tennessee, Knoxville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Innovative Comput. Lab. (ICL), Univ. of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029171875","display_name":"Guido Juckeland","orcid":"https://orcid.org/0000-0002-9935-4428"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guido Juckeland","raw_affiliation_strings":["Center for Inf. Services & High Performance Comput. (ZIH), Tech. Univ. Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Inf. Services & High Performance Comput. (ZIH), Tech. Univ. Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111475079","display_name":"Robert Dietrich","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert Dietrich","raw_affiliation_strings":["Center for Inf. Services & High Performance Comput. (ZIH), Tech. Univ. Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Inf. Services & High Performance Comput. (ZIH), Tech. Univ. Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004983255","display_name":"Duncan Poole","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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Duncan Poole","raw_affiliation_strings":["[Nvidia Corporation, Santa Clara, CA, USA]"],"affiliations":[{"raw_affiliation_string":"[Nvidia Corporation, Santa Clara, CA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086674060","display_name":"Christopher C. Lamb","orcid":"https://orcid.org/0000-0003-3398-6382"},"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christopher Lamb","raw_affiliation_strings":["[Nvidia Corporation, Santa Clara, CA, USA]"],"affiliations":[{"raw_affiliation_string":"[Nvidia Corporation, Santa Clara, CA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.224,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":80,"citation_normalized_percentile":{"value":0.966492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"185"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9995,"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":0.9994,"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/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.70513546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85832685},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8434919},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.72825146},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.70513546},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6528706},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.57306325},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.48652118},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46713662},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.45506617},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42395103},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39712554},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22822353},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2083618},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.091713786},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpp.2011.71","pdf_url":null,"source":{"id":"https://openalex.org/S4306424025","display_name":"International Conference on Parallel Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":13,"referenced_works":["https://openalex.org/W1480411462","https://openalex.org/W153244122","https://openalex.org/W1559603603","https://openalex.org/W1656664476","https://openalex.org/W1762731526","https://openalex.org/W1965351873","https://openalex.org/W1969399184","https://openalex.org/W1978889278","https://openalex.org/W2136434791","https://openalex.org/W2149234156","https://openalex.org/W2162322364","https://openalex.org/W2395771004","https://openalex.org/W2398736067"],"related_works":["https://openalex.org/W4394633758","https://openalex.org/W3048701459","https://openalex.org/W3037515626","https://openalex.org/W2502510154","https://openalex.org/W240129890","https://openalex.org/W2389600408","https://openalex.org/W2364044215","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W1963859303"],"abstract_inverted_index":{"The":[0],"power":[1],"of":[2,34],"GPUs":[3],"is":[4],"giving":[5],"rise":[6],"to":[7,21,50,96],"heterogeneous":[8,35,40,59],"parallel":[9,60],"computing,":[10],"with":[11,31,37],"new":[12,56,79],"demands":[13],"on":[14],"programming":[15],"environments,":[16],"runtime":[17],"systems,":[18],"and":[19,43,70,101],"tools":[20],"deliver":[22],"high-performing":[23],"applications.":[24],"This":[25],"paper":[26],"studies":[27],"the":[28,52,71,78,91,98],"problems":[29],"associated":[30],"performance":[32,61],"measurement":[33,46,62,99],"machines":[36],"GPUs.":[38],"A":[39],"computation":[41],"model":[42],"alternative":[44],"host-GPU":[45],"approaches":[47],"are":[48,94],"discussed":[49],"set":[51],"stage":[53],"for":[54,58],"reporting":[55],"capabilities":[57],"in":[63,83],"three":[64],"leading":[65],"HPC":[66],"tools:":[67],"PAPI,":[68],"Vampir,":[69],"TAU":[72],"Performance":[73],"System.":[74],"Our":[75],"work":[76],"leverages":[77],"CUPTI":[80],"tool":[81,102],"support":[82],"NVIDIA's":[84],"CUDA":[85],"device":[86],"library.":[87],"Heterogeneous":[88],"benchmarks":[89],"from":[90],"SHOC":[92],"suite":[93],"used":[95],"demonstrate":[97],"methods":[100],"support.":[103]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2122002474","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":7}],"updated_date":"2024-12-07T12:28:53.566140","created_date":"2016-06-24"}
