{"id":"https://openalex.org/W1642509926","doi":"https://doi.org/10.1109/icacci.2015.7275658","title":"Scaling number of cores in GPGPU: A comparative performance analysis","display_name":"Scaling number of cores in GPGPU: A comparative performance analysis","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W1642509926","doi":"https://doi.org/10.1109/icacci.2015.7275658","mag":"1642509926"},"language":"en","primary_location":{"id":"doi:10.1109/icacci.2015.7275658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2015.7275658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","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/A5011782290","display_name":"Winnie Thomas","orcid":"https://orcid.org/0000-0001-8341-2403"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Winnie Thomas","raw_affiliation_strings":["Department of Electrical Engineering, Veermata Jijabai Technological Institute, Mumbai, India","[Department of Electrical Engineering, Veermata Jijabai Technological Institute, Mumbai, INDIA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Veermata Jijabai Technological Institute, Mumbai, India","institution_ids":[]},{"raw_affiliation_string":"[Department of Electrical Engineering, Veermata Jijabai Technological Institute, Mumbai, INDIA]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015094108","display_name":"Rohin Daruwala","orcid":"https://orcid.org/0000-0002-3267-6270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohin D. Daruwala","raw_affiliation_strings":["Department of Electrical Engineering, Veermata Jijabai Technological Institute, Mumbai, India","[Department of Electrical Engineering, Veermata Jijabai Technological Institute, Mumbai, INDIA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Veermata Jijabai Technological Institute, Mumbai, India","institution_ids":[]},{"raw_affiliation_string":"[Department of Electrical Engineering, Veermata Jijabai Technological Institute, Mumbai, INDIA]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011782290"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03829864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"68","issue":null,"first_page":"501","last_page":"507"},"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":0.9994000196456909,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8714061975479126},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8241773843765259},{"id":"https://openalex.org/keywords/shader","display_name":"Shader","score":0.6593543887138367},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6078245639801025},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.6062614917755127},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.47151055932044983},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4579422175884247},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.338559627532959},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3342364728450775},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21224111318588257},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.15267735719680786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8714061975479126},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8241773843765259},{"id":"https://openalex.org/C177681979","wikidata":"https://www.wikidata.org/wiki/Q633182","display_name":"Shader","level":3,"score":0.6593543887138367},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6078245639801025},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.6062614917755127},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.47151055932044983},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4579422175884247},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.338559627532959},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3342364728450775},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21224111318588257},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.15267735719680786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icacci.2015.7275658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2015.7275658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1559378205","https://openalex.org/W1762731526","https://openalex.org/W1979527452","https://openalex.org/W1983235612","https://openalex.org/W1984222112","https://openalex.org/W2000335122","https://openalex.org/W2001828452","https://openalex.org/W2048441570","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2128022558","https://openalex.org/W2142444503","https://openalex.org/W2155503253","https://openalex.org/W2614852291","https://openalex.org/W3137551601","https://openalex.org/W4235870392","https://openalex.org/W6638054461","https://openalex.org/W6738282062"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W74409296","https://openalex.org/W2003935582","https://openalex.org/W1554644772","https://openalex.org/W305742777","https://openalex.org/W2567390125","https://openalex.org/W1638215063","https://openalex.org/W2468095077","https://openalex.org/W2121547511","https://openalex.org/W2940653809"],"abstract_inverted_index":{"The":[0,85,178],"Single":[1],"Instruction":[2,19],"Multiple":[3,18,20],"Thread":[4,46],"(SIMT)":[5],"architecture":[6],"based,":[7],"Graphic":[8],"Processing":[9],"Units":[10],"(GPUs)":[11],"are":[12,42,55,65,164],"emerging":[13],"as":[14,58],"more":[15],"efficient":[16],"than":[17],"Data":[21],"(MIMD)":[22],"architectures":[23],"in":[24,88,161,182,241,246],"exploiting":[25,110],"parallelism.":[26],"A":[27],"GPU":[28,91,133],"has":[29],"numerous":[30],"shader":[31,98,223],"cores":[32,99,116,170,224],"and":[33,117,144,230],"thousands":[34],"of":[35,109,115,123,130,169,184,200,204,222,239,243],"simultaneous":[36],"fine-grained":[37],"active":[38],"threads.":[39],"These":[40],"threads":[41,51],"grouped":[43,57],"into":[44,135],"Cooperative":[45],"Arrays":[47],"(CTAs).":[48],"All":[49],"the":[50,70,136,145,156,198,237],"within":[52,62],"a":[53,63,79,90,128,231],"CTA":[54,64],"further":[56],"warps.":[59],"Though":[60],"warps":[61,103],"scheduled":[66],"for":[67,191,207,227],"execution":[68],"on":[69,120,202,216],"same":[71],"core,":[72],"only":[73],"one":[74],"warp":[75],"is":[76,94,150,189,225],"executed":[77],"at":[78,236],"time":[80],"due":[81],"to":[82,100,233],"hardware":[83],"constraint.":[84],"subsequent":[86],"way":[87,108],"which":[89],"exploits":[92],"parallelism":[93,111],"by":[95,112,219],"employing":[96],"multiple":[97,102],"execute":[101],"simultaneously.":[104],"We":[105,125,153,195],"explore":[106],"latter":[107],"increasing":[113],"number":[114,129,168,221],"its":[118,162],"impact":[119,199],"different":[121],"types":[122],"applications.":[124],"first":[126],"categorize":[127],"general":[131],"purpose":[132],"workloads":[134,157,174,229,235],"ones":[137,146],"that":[138,155,158,213],"consumes":[139],"less":[140],"(L)":[141],"DRAM":[142],"bandwidth":[143,148,217],"whose":[147],"requirement":[149],"heavier":[151],"(H).":[152],"observed":[154,197],"get":[159],"boost":[160,232],"performance":[163,176,180],"under":[165],"type-L":[166,234],"when":[167],"increase.":[171],"Whereas":[172],"type-H":[173,228],"experience":[175],"degradation.":[177],"maximum":[179],"gain":[181],"terms":[183],"instructions":[185],"per":[186],"cycle":[187],"(IPC),":[188],"2.03x":[190],"type":[192],"-L":[193],"workloads.":[194,209],"then":[196],"scaling":[201,220],"percentage":[203,242],"good":[205,244],"cycles":[206,245],"all":[208],"Our":[210],"results":[211],"show":[212],"additional":[214],"pressure":[215],"caused":[218],"detrimental":[226],"cost":[238],"reduction":[240],"both":[247],"types.":[248]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}