{"id":"https://openalex.org/W2232645663","doi":"https://doi.org/10.1145/2830772.2830813","title":"Enabling coordinated register allocation and thread-level parallelism optimization for GPUs","display_name":"Enabling coordinated register allocation and thread-level parallelism optimization for GPUs","publication_year":2015,"publication_date":"2015-12-05","ids":{"openalex":"https://openalex.org/W2232645663","doi":"https://doi.org/10.1145/2830772.2830813","mag":"2232645663"},"language":"en","primary_location":{"id":"doi:10.1145/2830772.2830813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830772.2830813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","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/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":["Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, 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":["Peking University, China and Collaborative Innovation Center of High Performance Computing, NUDT, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, China and Collaborative Innovation Center of High Performance Computing, NUDT, 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":["Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, 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":["Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, 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":["Peking University, China and Collaborative Innovation Center of High Performance Computing, NUDT, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, China and Collaborative Innovation Center of High Performance Computing, NUDT, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453708","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0003-4310-4056"},"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":["Peking University, China and Collaborative Innovation Center of High Performance Computing, NUDT, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, China and Collaborative Innovation Center of High Performance Computing, NUDT, 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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongrui Fan","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.8597,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.98955095,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"395","last_page":"406"},"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":0.9986000061035156,"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":0.998199999332428,"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":0.845281720161438},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.8147822618484497},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7282167077064514},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.6612827181816101},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.6247094869613647},{"id":"https://openalex.org/keywords/bandwidth-throttling","display_name":"Bandwidth throttling","score":0.5649124979972839},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5291533470153809},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.46954473853111267},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4622603952884674},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.46001124382019043},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.3466408848762512},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.1241661012172699}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845281720161438},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.8147822618484497},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7282167077064514},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.6612827181816101},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.6247094869613647},{"id":"https://openalex.org/C173061102","wikidata":"https://www.wikidata.org/wiki/Q478819","display_name":"Bandwidth throttling","level":3,"score":0.5649124979972839},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5291533470153809},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.46954473853111267},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4622603952884674},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.46001124382019043},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.3466408848762512},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.1241661012172699},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C131097465","wikidata":"https://www.wikidata.org/wiki/Q178898","display_name":"Gas compressor","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2830772.2830813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830772.2830813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","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":46,"referenced_works":["https://openalex.org/W1498962072","https://openalex.org/W1968775993","https://openalex.org/W1970643910","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/W2067441262","https://openalex.org/W2079038734","https://openalex.org/W2079248286","https://openalex.org/W2080592089","https://openalex.org/W2084110734","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/W2140191557","https://openalex.org/W2142444503","https://openalex.org/W2147193503","https://openalex.org/W2152517358","https://openalex.org/W2167334577","https://openalex.org/W2167399819","https://openalex.org/W2169880332","https://openalex.org/W3152438252","https://openalex.org/W4205241946","https://openalex.org/W4237024478"],"related_works":["https://openalex.org/W2145021874","https://openalex.org/W4239584669","https://openalex.org/W2045555750","https://openalex.org/W2034724838","https://openalex.org/W4250432526","https://openalex.org/W1521414776","https://openalex.org/W2101536355","https://openalex.org/W2009783759","https://openalex.org/W2171651200","https://openalex.org/W2224192221"],"abstract_inverted_index":{"The":[0],"key":[1],"to":[2,12,38,43,59,68,85,99,104],"high":[3],"performance":[4,41,116],"on":[5],"GPUs":[6,77],"lies":[7],"in":[8],"the":[9,18,29,39,44,61,70,74,122,128],"massive":[10],"threading":[11],"enable":[13,86],"thread":[14,46,54,93],"switching":[15],"and":[16,23],"hide":[17],"latency":[19],"of":[20,63,107],"function":[21],"unit":[22],"memory":[24],"access.":[25],"However,":[26,92],"running":[27],"with":[28,80],"maximum":[30],"thread-level":[31],"parallelism":[32],"(TLP)":[33],"does":[34],"not":[35,119],"necessarily":[36],"lead":[37,103],"optimal":[40],"due":[42],"excessive":[45],"contention":[47],"for":[48,115],"cache":[49,101],"resource.":[50],"As":[51],"a":[52,81,112],"result,":[53],"throttling":[55,94],"techniques":[56,95],"are":[57,78,97],"employed":[58],"limit":[60],"number":[62],"threads":[64],"that":[65,96],"concurrently":[66],"execute":[67],"preserve":[69],"data":[71],"locality.":[72],"On":[73],"other":[75],"hand,":[76],"equipped":[79],"large":[82],"register":[83],"file":[84],"fast":[87],"context":[88],"switch":[89],"between":[90],"threads.":[91],"designed":[98],"mitigate":[100],"contention,":[102],"under":[105],"utilization":[106],"registers.":[108],"Register":[109],"allocation":[110],"is":[111],"significant":[113],"factor":[114],"as":[117],"it":[118],"just":[120],"determines":[121],"single-thread":[123],"performance,":[124],"but":[125],"indirectly":[126],"affects":[127],"TLP.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
