{"id":"https://openalex.org/W4381389685","doi":"https://doi.org/10.1145/3589236.3589245","title":"Lightweight Register File Caching in Collector Units for GPUs","display_name":"Lightweight Register File Caching in Collector Units for GPUs","publication_year":2023,"publication_date":"2023-02-25","ids":{"openalex":"https://openalex.org/W4381389685","doi":"https://doi.org/10.1145/3589236.3589245"},"language":"en","primary_location":{"id":"doi:10.1145/3589236.3589245","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589236.3589245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2117/390429","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092217297","display_name":"Mojtaba Abaie Shoushtary","orcid":"https://orcid.org/0000-0003-2377-6939"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Mojtaba Abaie Shoushtary","raw_affiliation_strings":["Polytechnic University of Catalonia, Spain"],"raw_orcid":"https://orcid.org/0000-0003-2377-6939","affiliations":[{"raw_affiliation_string":"Polytechnic University of Catalonia, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032189355","display_name":"Jos\u00e9-Mar\u00eda Arnau","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose Maria Arnau","raw_affiliation_strings":["Polytechnic University of Catalonia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-0336-9191","affiliations":[{"raw_affiliation_string":"Polytechnic University of Catalonia, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007317670","display_name":"Jordi Tubella Murgadas","orcid":"https://orcid.org/0000-0001-8669-0740"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Tubella Murgadas","raw_affiliation_strings":["Polytechnic University of Catalonia, Spain"],"raw_orcid":"https://orcid.org/0000-0001-8669-0740","affiliations":[{"raw_affiliation_string":"Polytechnic University of Catalonia, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100733331","display_name":"Antonio Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-0009-0996"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Gonzalez","raw_affiliation_strings":["Polytechnic University of Catalonia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-0009-0996","affiliations":[{"raw_affiliation_string":"Polytechnic University of Catalonia, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092217297"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":1.1884,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76223137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"33"},"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":0.9991000294685364,"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":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.85548996925354},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.8146427869796753},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6323282718658447},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6088680028915405},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5644619464874268},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5454140901565552},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5324465036392212},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5115848183631897},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4774352014064789},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4587633013725281},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.43826228380203247},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3483829200267792},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32834580540657043},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.25878670811653137},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.1739930808544159}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85548996925354},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.8146427869796753},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6323282718658447},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6088680028915405},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5644619464874268},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5454140901565552},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5324465036392212},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5115848183631897},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4774352014064789},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4587633013725281},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.43826228380203247},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3483829200267792},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32834580540657043},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.25878670811653137},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.1739930808544159},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3589236.3589245","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589236.3589245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/390429","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/390429","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/390429","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/390429","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2022632182","https://openalex.org/W2047060659","https://openalex.org/W2080592089","https://openalex.org/W2096661534","https://openalex.org/W2789977517","https://openalex.org/W2963989532","https://openalex.org/W3100327344","https://openalex.org/W3102510044","https://openalex.org/W3206857466"],"related_works":["https://openalex.org/W3144620029","https://openalex.org/W2356166161","https://openalex.org/W2155131180","https://openalex.org/W2139082473","https://openalex.org/W2042399072","https://openalex.org/W2130533867","https://openalex.org/W2540018280","https://openalex.org/W2045163867","https://openalex.org/W2059502833","https://openalex.org/W2096854345"],"abstract_inverted_index":{"Modern":[0],"GPUs":[1,46],"benefit":[2],"from":[3],"a":[4,24,35,98,119],"sizable":[5],"Register":[6],"File":[7],"(RF)":[8],"to":[9],"provide":[10],"fine-grained":[11],"thread":[12],"switching.":[13],"As":[14],"the":[15,28,32,95,102],"RF":[16,38,55,103],"is":[17,47,61,85],"huge":[18],"and":[19,43,70,78,107],"accessed":[20],"frequently,":[21],"it":[22],"consumes":[23],"considerable":[25],"share":[26],"of":[27,31,122],"dynamic":[29,108],"energy":[30,41,109],"GPU.":[33],"Designing":[34],"large,":[36],"high-throughput":[37],"with":[39,118],"low":[40],"consumption":[42],"area":[44],"for":[45,57],"challenging.":[48],"In":[49],"this":[50],"paper,":[51],"an":[52],"energy-efficient":[53,67],"hierarchical":[54],"design":[56],"GPUs,":[58],"called":[59],"Malekeh,":[60],"introduced.":[62],"Malekeh":[63,100],"keeps":[64],"registers":[65],"in":[66,124],"small":[68],"caches":[69],"maximizes":[71],"cache":[72],"efficacy":[73],"by":[74,87,94,105,110,116],"using":[75],"lightweight":[76],"policies":[77],"supporting":[79],"adaptive":[80],"algorithms.":[81],"The":[82],"policies\u2019":[83],"effectiveness":[84],"improved":[86],"leveraging":[88],"register":[89],"reuse":[90],"distance":[91],"information":[92],"provided":[93],"compiler":[96],"as":[97],"hint.":[99],"reduces":[101],"reads":[104],"48.5%":[106],"29.1%.":[111],"It":[112],"also":[113],"improves":[114],"performance":[115],"9.6%":[117],"negligible":[120],"overhead":[121],"0.04%":[123],"area.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2023-06-21T00:00:00"}
