{"id":"https://openalex.org/W2989532353","doi":"https://doi.org/10.1109/lca.2019.2951161","title":"LOOG: Improving GPU Efficiency With Light-Weight Out-Of-Order Execution","display_name":"LOOG: Improving GPU Efficiency With Light-Weight Out-Of-Order Execution","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2989532353","doi":"https://doi.org/10.1109/lca.2019.2951161","mag":"2989532353"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2019.2951161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2019.2951161","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-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/A5006425693","display_name":"Konstantinos Iliakis","orcid":"https://orcid.org/0000-0002-1403-6851"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Konstantinos Iliakis","raw_affiliation_strings":["National Technical University of Athens, Zografou, Greece"],"raw_orcid":"https://orcid.org/0000-0002-1403-6851","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, Zografou, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076432415","display_name":"Sotirios Xydis","orcid":"https://orcid.org/0000-0003-3151-2730"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Sotirios Xydis","raw_affiliation_strings":["National Technical University of Athens, Zografou, Greece"],"raw_orcid":"https://orcid.org/0000-0003-3151-2730","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, Zografou, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043131021","display_name":"Dimitrios Soudris","orcid":"https://orcid.org/0000-0002-6930-6847"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Soudris","raw_affiliation_strings":["National Technical University of Athens, Zografou, Greece"],"raw_orcid":"https://orcid.org/0000-0002-6930-6847","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, Zografou, Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006425693"],"corresponding_institution_ids":["https://openalex.org/I174458059"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.15396303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"18","issue":"2","first_page":"166","last_page":"169"},"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":0.9973000288009644,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.910645604133606},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7291750907897949},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7136454582214355},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5522456765174866},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.5496153831481934},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5398736000061035},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5285082459449768},{"id":"https://openalex.org/keywords/out-of-order-execution","display_name":"Out-of-order execution","score":0.5020191669464111},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.49976587295532227},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4544643759727478},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4539759159088135},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.44331610202789307},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4160251319408417},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36685773730278015},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.24743738770484924},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22543242573738098},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.14902269840240479},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11519438028335571}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.910645604133606},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7291750907897949},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7136454582214355},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5522456765174866},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.5496153831481934},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5398736000061035},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5285082459449768},{"id":"https://openalex.org/C1793878","wikidata":"https://www.wikidata.org/wiki/Q1153762","display_name":"Out-of-order execution","level":2,"score":0.5020191669464111},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.49976587295532227},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4544643759727478},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4539759159088135},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.44331610202789307},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4160251319408417},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36685773730278015},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.24743738770484924},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22543242573738098},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.14902269840240479},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11519438028335571},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2019.2951161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2019.2951161","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1555915743","https://openalex.org/W1968775993","https://openalex.org/W1979527452","https://openalex.org/W1997162567","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2142444503","https://openalex.org/W2170382128","https://openalex.org/W2273440736","https://openalex.org/W2315868086","https://openalex.org/W2517837804","https://openalex.org/W2593733978","https://openalex.org/W2936491961","https://openalex.org/W4230022086","https://openalex.org/W4255847023","https://openalex.org/W6694513646"],"related_works":["https://openalex.org/W2091793939","https://openalex.org/W2111412181","https://openalex.org/W2055881261","https://openalex.org/W2120628323","https://openalex.org/W2171175484","https://openalex.org/W4255052811","https://openalex.org/W2085872434","https://openalex.org/W4250432526","https://openalex.org/W2101536355","https://openalex.org/W2562747857"],"abstract_inverted_index":{"GPUs":[0,22],"are":[1],"one":[2],"of":[3,46,55,62,81,135,145,163],"the":[4,38,60,107,114,143],"most":[5],"prevalent":[6],"platforms":[7,119],"for":[8,127],"accelerating":[9],"general-purpose":[10,165],"workloads":[11],"due":[12],"to":[13,31,50,58,104,122,137],"their":[14],"intuitive":[15],"programming":[16],"model,":[17],"computing":[18],"capacity,":[19],"and":[20,27,65,84],"cost-effectiveness.":[21],"rely":[23],"on":[24,125],"massive":[25],"multi-threading":[26],"fast":[28],"context":[29],"switching":[30],"overlap":[32],"computations":[33],"with":[34,90,131,167],"memory":[35,63],"operations.":[36],"Among":[37],"diverse":[39],"GPU":[40,150],"workloads,":[41],"there":[42],"exists":[43],"a":[44,52,87,149,155,160],"class":[45],"kernels":[47,75,166],"that":[48,73,113],"fail":[49],"maintain":[51],"sufficient":[53],"number":[54],"active":[56],"warps":[57],"hide":[59],"latency":[61],"operations,":[64],"thus":[66],"suffer":[67],"from":[68,78],"frequent":[69],"stalling.":[70],"We":[71,111],"observe":[72],"these":[74],"will":[76],"benefit":[77],"increased":[79],"levels":[80],"Instruction-Level":[82],"Parallelism":[83],"we":[85,99,141],"propose":[86],"novel":[88],"architecture":[89,116],"lightweight":[91],"Out-Of-Order":[92],"execution":[93],"capability.":[94],"To":[95],"minimize":[96],"hardware":[97],"overheads,":[98],"carefully":[100],"design":[101],"our":[102,146],"extension":[103],"highly":[105],"re-use":[106],"existing":[108],"micro-architectural":[109],"structures.":[110],"show":[112],"proposed":[115],"outperforms":[117],"traditional":[118],"by":[120,153],"15":[121],"46":[123],"percent":[124,157,172],"average":[126],"low":[128],"occupancy":[129],"kernels,":[130],"an":[132],"area":[133,173],"overhead":[134],"0.74":[136,171],"3.94":[138],"percent.":[139],"Finally,":[140],"prove":[142],"potential":[144],"proposal":[147],"as":[148,168,170],"u-arch":[151],"alternative,":[152],"providing":[154],"5":[156],"speedup":[158],"over":[159],"wide":[161],"collection":[162],"63":[164],"little":[169],"overhead.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}