{"id":"https://openalex.org/W2054782014","doi":"https://doi.org/10.1109/samos.2014.6893202","title":"GPGPU workload characteristics and performance analysis","display_name":"GPGPU workload characteristics and performance analysis","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2054782014","doi":"https://doi.org/10.1109/samos.2014.6893202","mag":"2054782014"},"language":"en","primary_location":{"id":"doi:10.1109/samos.2014.6893202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/samos.2014.6893202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS XIV)","raw_type":"proceedings-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/A5083072467","display_name":"Sohan Lal","orcid":"https://orcid.org/0000-0002-2325-1705"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sohan Lal","raw_affiliation_strings":["Embedded Systems Architecture, TU Berlin, Berlin, Germany","Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany"],"affiliations":[{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110305136","display_name":"Jan Lucas","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Lucas","raw_affiliation_strings":["Embedded Systems Architecture, TU Berlin, Berlin, Germany","Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany"],"affiliations":[{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008915989","display_name":"Michael Andersch","orcid":"https://orcid.org/0009-0004-5778-4480"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Andersch","raw_affiliation_strings":["Embedded Systems Architecture, TU Berlin, Berlin, Germany","Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany"],"affiliations":[{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064650557","display_name":"Mauricio \u00c1lvarez-Mesa","orcid":"https://orcid.org/0000-0002-1751-0993"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mauricio Alvarez-Mesa","raw_affiliation_strings":["Embedded Systems Architecture, TU Berlin, Berlin, Germany","Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany"],"affiliations":[{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027045231","display_name":"Ahmed Elhossini","orcid":"https://orcid.org/0000-0001-7389-9473"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ahmed Elhossini","raw_affiliation_strings":["Embedded Systems Architecture, TU Berlin, Berlin, Germany","Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany"],"affiliations":[{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112321355","display_name":"Ben Juurlink","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ben Juurlink","raw_affiliation_strings":["Embedded Systems Architecture, TU Berlin, Berlin, Germany","Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany"],"affiliations":[{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Embedded Systems Architecture, TU Berlin, Einsteinufer 17, D-10587, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5083072467"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":1.2602,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.7993351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":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":0.9994999766349792,"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":0.9993000030517578,"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":0.7833817005157471},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6926267743110657},{"id":"https://openalex.org/keywords/occupancy","display_name":"Occupancy","score":0.670272171497345},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.6128856539726257},{"id":"https://openalex.org/keywords/electrical-efficiency","display_name":"Electrical efficiency","score":0.6066495776176453},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5625722408294678},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.5245119333267212},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.468995600938797},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.4538721442222595},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43709057569503784},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4267018437385559},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42084550857543945},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.3597346246242523},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18066951632499695},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1255684196949005},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12388262152671814},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09502390027046204},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08079773187637329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833817005157471},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6926267743110657},{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.670272171497345},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.6128856539726257},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.6066495776176453},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5625722408294678},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.5245119333267212},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.468995600938797},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.4538721442222595},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43709057569503784},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4267018437385559},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42084550857543945},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3597346246242523},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18066951632499695},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1255684196949005},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12388262152671814},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09502390027046204},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08079773187637329},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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":2,"locations":[{"id":"doi:10.1109/samos.2014.6893202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/samos.2014.6893202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS XIV)","raw_type":"proceedings-article"},{"id":"pmh:oai:tore.tuhh.de:11420/12321","is_oa":false,"landing_page_url":"http://hdl.handle.net/11420/12321","pdf_url":null,"source":{"id":"https://openalex.org/S4306401751","display_name":"tub.dok (Hamburg University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I884043246","host_organization_name":"Hamburg University of Technology","host_organization_lineage":["https://openalex.org/I884043246"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8899999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W1997162567","https://openalex.org/W2006312753","https://openalex.org/W2008185810","https://openalex.org/W2024122052","https://openalex.org/W2055881261","https://openalex.org/W2078994750","https://openalex.org/W2080592089","https://openalex.org/W2092340922","https://openalex.org/W2093043622","https://openalex.org/W2096661534","https://openalex.org/W2126256127","https://openalex.org/W2149693551","https://openalex.org/W2254254903","https://openalex.org/W2614044057","https://openalex.org/W6651700774","https://openalex.org/W6691950125","https://openalex.org/W6737597861"],"related_works":["https://openalex.org/W2191246539","https://openalex.org/W1585350690","https://openalex.org/W2008876287","https://openalex.org/W4245302940","https://openalex.org/W2074226157","https://openalex.org/W2094969226","https://openalex.org/W1606851719","https://openalex.org/W1997955449","https://openalex.org/W2152610519","https://openalex.org/W2054782014"],"abstract_inverted_index":{"GPUs":[0,20],"are":[1,44,141],"much":[2,23],"more":[3],"power-efficient":[4,48],"devices":[5],"compared":[6],"to":[7,11,46,59],"CPUs,":[8],"but":[9],"due":[10],"several":[12],"performance":[13,16,36,95,104,127],"bottlenecks,":[14],"the":[15,61,70,90,102,114,122,132],"per":[17],"watt":[18],"of":[19],"is":[21,57],"often":[22],"lower":[24],"than":[25],"what":[26],"could":[27],"be":[28],"achieved":[29],"theoretically.":[30],"To":[31,51],"sustain":[32],"and":[33,41,68,88,96,109,128],"continue":[34],"high":[35],"computing":[37,49],"growth,":[38],"new":[39],"architectural":[40],"application":[42],"techniques":[43],"required":[45],"create":[47],"systems.":[50],"find":[52],"such":[53],"techniques,":[54],"however,":[55],"it":[56],"necessary":[58],"study":[60,81,119],"power":[62,83],"consumption":[63,84],"at":[64,85],"a":[65],"detailed":[66],"level":[67,87],"understand":[69],"bottlenecks":[71,91],"which":[72],"cause":[73,93],"low":[74,94,97,103,107,115],"performance.":[75],"Therefore,":[76],"in":[77,125],"this":[78],"paper,":[79],"we":[80,118,136],"GPU":[82],"component":[86],"investigate":[89,137],"that":[92],"energy":[98,129],"efficiency.":[99,130],"We":[100],"divide":[101],"kernels":[105,140],"into":[106],"occupancy":[108,111,116,123,134],"full":[110,133],"categories.":[112],"For":[113,131],"category,":[117,135],"if":[120,138],"increasing":[121,126],"helps":[124],"these":[139],"limited":[142],"by":[143],"memory":[144],"bandwidth,":[145],"coalescing":[146],"efficiency,":[147],"or":[148],"SIMD":[149],"utilization.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
