{"id":"https://openalex.org/W2769375938","doi":"https://doi.org/10.1109/tc.2017.2776272","title":"CRAT: Enabling Coordinated Register Allocation and Thread-Level Parallelism Optimization for GPUs","display_name":"CRAT: Enabling Coordinated Register Allocation and Thread-Level Parallelism Optimization for GPUs","publication_year":2017,"publication_date":"2017-11-24","ids":{"openalex":"https://openalex.org/W2769375938","doi":"https://doi.org/10.1109/tc.2017.2776272","mag":"2769375938"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2017.2776272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2017.2776272","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Transactions on Computers","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/A5101761686","display_name":"Xiaolong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Xie","raw_affiliation_strings":["Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9113-3949","affiliations":[{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9076-7998","affiliations":[{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663885","display_name":"Xiuhong Li","orcid":"https://orcid.org/0000-0002-5327-0907"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuhong Li","raw_affiliation_strings":["Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030162440","display_name":"Yudong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Wu","raw_affiliation_strings":["Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850376","display_name":"Guangyu Sun","orcid":"https://orcid.org/0000-0001-6436-0820"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Sun","raw_affiliation_strings":["Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453685","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0003-2833-1592"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011407484","display_name":"Dongrui Fan","orcid":"https://orcid.org/0000-0001-5219-0908"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongrui Fan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5929,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8587343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"67","issue":"6","first_page":"890","last_page":"897"},"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":0.9988999962806702,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7955994606018066},{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.7907586097717285},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.768110990524292},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7629600167274475},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7270137071609497},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.6224427223205566},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5707054138183594},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5540739297866821},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5428289771080017},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.3113289177417755},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.29565614461898804},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.2541295289993286},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1840360164642334},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18044108152389526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955994606018066},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.7907586097717285},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.768110990524292},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7629600167274475},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7270137071609497},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.6224427223205566},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5707054138183594},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5540739297866821},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5428289771080017},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.3113289177417755},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.29565614461898804},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.2541295289993286},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1840360164642334},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18044108152389526},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2017.2776272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2017.2776272","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8722444188","display_name":"\u9762\u5411\u4e0d\u89c4\u5219GPU\u5e94\u7528\u7684\u5206\u6790\u4e0e\u4f18\u5316\u6280\u672f\u7814\u7a76","funder_award_id":"61672048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1498962072","https://openalex.org/W1968775993","https://openalex.org/W1970815868","https://openalex.org/W1972077953","https://openalex.org/W1972971542","https://openalex.org/W1979527452","https://openalex.org/W1982996921","https://openalex.org/W1983235612","https://openalex.org/W2003804316","https://openalex.org/W2009946006","https://openalex.org/W2022632182","https://openalex.org/W2025567168","https://openalex.org/W2027806965","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2059301531","https://openalex.org/W2061313045","https://openalex.org/W2062527253","https://openalex.org/W2067441262","https://openalex.org/W2079038734","https://openalex.org/W2079248286","https://openalex.org/W2080592089","https://openalex.org/W2081583983","https://openalex.org/W2084309410","https://openalex.org/W2090584832","https://openalex.org/W2091553595","https://openalex.org/W2093043622","https://openalex.org/W2098505406","https://openalex.org/W2100409742","https://openalex.org/W2106018915","https://openalex.org/W2107333973","https://openalex.org/W2113282196","https://openalex.org/W2115676933","https://openalex.org/W2123440268","https://openalex.org/W2126830109","https://openalex.org/W2129232868","https://openalex.org/W2142444503","https://openalex.org/W2147193503","https://openalex.org/W2152517358","https://openalex.org/W2160428323","https://openalex.org/W2167334577","https://openalex.org/W2167399819","https://openalex.org/W2169880332","https://openalex.org/W2232645663","https://openalex.org/W2235724720","https://openalex.org/W2235785597","https://openalex.org/W2236252626","https://openalex.org/W2238992335","https://openalex.org/W2239144794","https://openalex.org/W2323693848","https://openalex.org/W2346977986","https://openalex.org/W2398414514","https://openalex.org/W2510697685","https://openalex.org/W2510980549","https://openalex.org/W2518607193","https://openalex.org/W2564688911","https://openalex.org/W2566334102","https://openalex.org/W2951810231","https://openalex.org/W3137551601","https://openalex.org/W3152438252","https://openalex.org/W4237024478","https://openalex.org/W4239017056","https://openalex.org/W4239965559","https://openalex.org/W4253306330","https://openalex.org/W6629932122"],"related_works":["https://openalex.org/W2111377238","https://openalex.org/W1967889241","https://openalex.org/W2165125411","https://openalex.org/W3022691489","https://openalex.org/W3117494601","https://openalex.org/W2161297616","https://openalex.org/W4247209662","https://openalex.org/W2224192221","https://openalex.org/W2884590322","https://openalex.org/W2238992335"],"abstract_inverted_index":{"The":[0],"key":[1],"to":[2,13,29,41,46,83,102,110,154],"the":[3,10,63,69,85,104,147],"high":[4],"performance":[5,57,148],"on":[6,94],"GPUs":[7,21],"lies":[8],"in":[9],"massive":[11],"threading":[12],"enable":[14,30],"thread":[15,35],"switching":[16],"and":[17,79,91,99,113,117],"hide":[18],"long":[19],"latencies.":[20],"are":[22,39],"equipped":[23],"with":[24],"a":[25,53],"large":[26],"register":[27,89,114,121],"file":[28],"fast":[31],"context":[32],"switch.":[33],"However,":[34],"throttling":[36],"techniques":[37],"that":[38,128],"designed":[40],"mitigate":[42],"cache":[43],"contention,":[44],"lead":[45],"under-utilization":[47],"of":[48,88,150],"registers.":[49],"Register":[50,77],"allocation":[51,90,115,122],"is":[52],"significant":[54],"factor":[55],"for":[56,123],"as":[58],"it":[59],"not":[60],"just":[61],"determines":[62],"single-thread":[64],"performance,":[65],"but":[66],"indirectly":[67],"affects":[68],"TLP.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"Coordinated":[76],"Allocation":[78],"Thread-level":[80],"parallelism":[81],"(CRAT)":[82],"explore":[84,111],"optimization":[86],"space":[87],"TLP":[92,112,137],"management":[93,138],"GPUs.":[95],"CRATemploys":[96],"both":[97],"compile-time(CRAT-static)":[98],"run-time":[100],"techniques(CRAT-dyn)":[101],"exhaust":[103],"design":[105],"space.":[106],"CRAT-static":[107,129,151],"works":[108],"statically":[109],"trade-off":[116],"CRAT-dyn":[118,144],"exploits":[119],"dynamic":[120],"further":[124,145],"improvement.":[125],"Experiments":[126],"indicate":[127],"achieves":[130],"an":[131],"average":[132],"1.25X":[133],"speedup":[134,149],"over":[135],"existing":[136],"technique.":[139],"On":[140],"four":[141],"register-limited":[142],"applications,":[143],"improves":[146],"from":[152],"1.51X":[153],"1.70X.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}