{"id":"https://openalex.org/W1843571901","doi":"https://doi.org/10.1145/2907294.2907298","title":"Improving GPU Performance Through Resource Sharing","display_name":"Improving GPU Performance Through Resource Sharing","publication_year":2016,"publication_date":"2016-05-31","ids":{"openalex":"https://openalex.org/W1843571901","doi":"https://doi.org/10.1145/2907294.2907298","mag":"1843571901"},"language":"en","primary_location":{"id":"doi:10.1145/2907294.2907298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2907294.2907298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing","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/A5068577522","display_name":"Vishwesh Jatala","orcid":"https://orcid.org/0000-0002-3105-922X"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vishwesh Jatala","raw_affiliation_strings":["Indian Institute of Technology, Kanpur, Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005790438","display_name":"Jayvant Anantpur","orcid":"https://orcid.org/0000-0003-3353-0625"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jayvant Anantpur","raw_affiliation_strings":["Indian Institute of Science, Bangalore, Bangalore, India","Indian Institute of Science Bangalore, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Indian Institute of Science Bangalore, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032981748","display_name":"Amey Karkare","orcid":"https://orcid.org/0000-0002-3664-6490"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amey Karkare","raw_affiliation_strings":["Indian Institute of Technology, Kanpur, Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068577522"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":2.2073,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86345684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"203","last_page":"214"},"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/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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9984999895095825,"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":0.8704804182052612},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.802311360836029},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.6574308276176453},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6247736215591431},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5667708516120911},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.48944345116615295},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.48575475811958313},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.37177544832229614},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.371591717004776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8704804182052612},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.802311360836029},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.6574308276176453},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6247736215591431},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5667708516120911},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.48944345116615295},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.48575475811958313},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.37177544832229614},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.371591717004776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2907294.2907298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2907294.2907298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1843571901","https://openalex.org/W1954658694","https://openalex.org/W1968775993","https://openalex.org/W1972971542","https://openalex.org/W1979527452","https://openalex.org/W2018150881","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2053744175","https://openalex.org/W2059301531","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2081583983","https://openalex.org/W2084110734","https://openalex.org/W2090584832","https://openalex.org/W2120062497","https://openalex.org/W2130749431","https://openalex.org/W2135947393","https://openalex.org/W2142444503","https://openalex.org/W2148443481","https://openalex.org/W2152956697","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2167675119","https://openalex.org/W2168921806","https://openalex.org/W2169880332","https://openalex.org/W2171793220","https://openalex.org/W2232645663","https://openalex.org/W2238992335","https://openalex.org/W2950141968","https://openalex.org/W3146509083"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W2101387113","https://openalex.org/W4206718021"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"consisting":[4],"of":[5,17,30,37,52,55,64,76],"Streaming":[6],"Multiprocessors":[7],"(SMs)":[8],"achieve":[9],"high":[10],"throughput":[11],"by":[12],"running":[13],"a":[14],"large":[15],"number":[16,29,36,51],"threads":[18,38,65],"and":[19,33,85],"context":[20],"switching":[21],"among":[22],"them":[23],"to":[24,66],"hide":[25],"execution":[26],"latencies.":[27],"The":[28],"thread":[31,59,72],"blocks,":[32],"hence":[34,86],"the":[35,48,58,62,71,77],"that":[39],"can":[40],"be":[41,81,88],"launched":[42],"on":[43,47],"an":[44,67],"SM,":[45],"depends":[46],"resource":[49],"usage--e.g.":[50],"registers,":[53],"amount":[54],"shared":[56],"memory--of":[57],"blocks.":[60],"Since":[61],"allocation":[63],"SM":[68],"is":[69],"at":[70],"block":[73],"granularity,":[74],"some":[75],"resources":[78],"may":[79],"not":[80],"used":[82],"up":[83],"completely":[84],"will":[87],"wasted.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}