{"id":"https://openalex.org/W2613066110","doi":"https://doi.org/10.1109/hpca.2017.51","title":"G-Scalar: Cost-Effective Generalized Scalar Execution Architecture for Power-Efficient GPUs","display_name":"G-Scalar: Cost-Effective Generalized Scalar Execution Architecture for Power-Efficient GPUs","publication_year":2017,"publication_date":"2017-02-01","ids":{"openalex":"https://openalex.org/W2613066110","doi":"https://doi.org/10.1109/hpca.2017.51","mag":"2613066110"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2017.51","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2017.51","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5086328631","display_name":"Zhenhong Liu","orcid":"https://orcid.org/0000-0002-8026-9629"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenhong Liu","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061356872","display_name":"Syed Gilani","orcid":"https://orcid.org/0000-0003-3129-3363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Syed Gilani","raw_affiliation_strings":["AMD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018033573","display_name":"Murali Annavaram","orcid":"https://orcid.org/0000-0002-4633-6867"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Annavaram","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"612"},"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":0.9987000226974487,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.7050362825393677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6687357425689697},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.5951159596443176},{"id":"https://openalex.org/keywords/scalar-multiplication","display_name":"Scalar multiplication","score":0.570107638835907},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5132040977478027},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.4833199977874756},{"id":"https://openalex.org/keywords/electrical-efficiency","display_name":"Electrical efficiency","score":0.42031610012054443},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.36857128143310547},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32161229848861694},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1841464340686798},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.15686357021331787},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1282080113887787}],"concepts":[{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.7050362825393677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6687357425689697},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.5951159596443176},{"id":"https://openalex.org/C171182647","wikidata":"https://www.wikidata.org/wiki/Q126736","display_name":"Scalar multiplication","level":3,"score":0.570107638835907},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5132040977478027},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.4833199977874756},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.42031610012054443},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.36857128143310547},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32161229848861694},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1841464340686798},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.15686357021331787},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1282080113887787},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":1,"locations":[{"id":"doi:10.1109/hpca.2017.51","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2017.51","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1485193134","https://openalex.org/W1970815868","https://openalex.org/W1971997351","https://openalex.org/W1979527452","https://openalex.org/W1991518265","https://openalex.org/W1994316441","https://openalex.org/W1998886328","https://openalex.org/W2026186397","https://openalex.org/W2042411977","https://openalex.org/W2043083835","https://openalex.org/W2052201685","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2093723220","https://openalex.org/W2095219408","https://openalex.org/W2096661534","https://openalex.org/W2118826546","https://openalex.org/W2125979435","https://openalex.org/W2131028454","https://openalex.org/W2138761132","https://openalex.org/W2143798346","https://openalex.org/W2155462892","https://openalex.org/W2160428323","https://openalex.org/W2162752393","https://openalex.org/W2170601541","https://openalex.org/W2273440736","https://openalex.org/W2322230929","https://openalex.org/W3148394109","https://openalex.org/W4256586690","https://openalex.org/W6629005405","https://openalex.org/W6678660376","https://openalex.org/W6679076360","https://openalex.org/W6681006065"],"related_works":["https://openalex.org/W2034604290","https://openalex.org/W2867317277","https://openalex.org/W2078886092","https://openalex.org/W1576294153","https://openalex.org/W2362283711","https://openalex.org/W2002792918","https://openalex.org/W2360049128","https://openalex.org/W1485234189","https://openalex.org/W4386773944","https://openalex.org/W2495172928"],"abstract_inverted_index":{"The":[0],"GPU":[1,93],"has":[2,95,119],"provide":[3],"higher":[4],"throughput":[5,28],"by":[6,146],"integrating":[7],"more":[8,73],"execution":[9,47,64,81],"resources":[10,111],"into":[11],"a":[12,43,152],"single":[13],"chip":[14],"without":[15],"unduly":[16],"compromising":[17],"power":[18,22,34,126,144],"efficiency.":[19,35],"With":[20],"the":[21,27,87,130,136],"wall":[23],"challenge,":[24],"however,":[25],"increasing":[26],"will":[29],"require":[30],"significant":[31],"improvement":[32],"in":[33,51,91],"To":[36],"accomplish":[37],"this":[38,52],"goal,":[39],"we":[40],"propose":[41],"G-Scalar,":[42],"cost-effective":[44],"generalized":[45],"scalar":[46,63,80,140],"architecture":[48],"for":[49,65],"GPUs":[50],"paper.":[53],"G-Scalar":[54,71,99,142],"offers":[55],"two":[56],"key":[57],"advantages":[58],"over":[59],"prior":[60],"architectures":[61],"supporting":[62],"only":[66],"non-divergent":[67],"arithmetic/logic":[68],"instructions.":[69],"First,":[70],"is":[72,100],"power-efficient":[74],"as":[75,103],"it":[76,104],"can":[77,105],"also":[78],"support":[79],"of":[82,89,108,116,128],"divergent":[83],"and":[84,138,148],"special-function":[85],"instructions,":[86],"fraction":[88],"which":[90,117],"contemporary":[92],"applications":[94],"notably":[96],"increased.":[97],"Second,":[98],"less":[101],"expensive":[102],"share":[106],"most":[107],"its":[109],"hardware":[110],"with":[112,135],"register":[113,132],"value":[114],"compression,":[115],"adoption":[118],"been":[120],"strongly":[121],"promoted":[122],"to":[123],"reduce":[124],"high":[125],"consumption":[127],"accessing":[129],"large":[131],"file.":[133],"Compared":[134],"baseline":[137],"previous":[139],"architectures,":[141],"improves":[143],"efficiency":[145],"24%":[147],"15%,":[149],"respectively,":[150],"at":[151],"negligible":[153],"cost.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}