{"id":"https://openalex.org/W2148060071","doi":"https://doi.org/10.1145/1596510.1596511","title":"Energy-efficient register caching with compiler assistance","display_name":"Energy-efficient register caching with compiler assistance","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2148060071","doi":"https://doi.org/10.1145/1596510.1596511","mag":"2148060071"},"language":"en","primary_location":{"id":"doi:10.1145/1596510.1596511","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1596510.1596511","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1596510.1596511","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/1596510.1596511","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047443783","display_name":"Timothy M. Jones","orcid":"https://orcid.org/0000-0002-4114-7661"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Timothy M. Jones","raw_affiliation_strings":["University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027001025","display_name":"Michael O\u2019Boyle","orcid":"https://orcid.org/0000-0003-1619-5052"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael F. P. O'Boyle","raw_affiliation_strings":["University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020861175","display_name":"Jaume Abella","orcid":"https://orcid.org/0000-0001-7951-4028"},"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"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Jaume Abella","raw_affiliation_strings":["Intel Labs Barcelona\u2014UPC"],"affiliations":[{"raw_affiliation_string":"Intel Labs Barcelona\u2014UPC","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733331","display_name":"Antonio Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-0009-0996"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Antonio Gonz\u00e1lez","raw_affiliation_strings":["Intel Labs Barcelona\u2014UPC"],"affiliations":[{"raw_affiliation_string":"Intel Labs Barcelona\u2014UPC","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052707216","display_name":"O\u011fuz Ergin","orcid":"https://orcid.org/0000-0003-2701-3787"},"institutions":[{"id":"https://openalex.org/I13236232","display_name":"TOBB University of Economics and Technology","ror":"https://ror.org/03ewx7v96","country_code":"TR","type":"education","lineage":["https://openalex.org/I13236232"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"O\u011fuz Ergin","raw_affiliation_strings":["TOBB University of Economics and Technology"],"affiliations":[{"raw_affiliation_string":"TOBB University of Economics and Technology","institution_ids":["https://openalex.org/I13236232"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047443783"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.3399,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.82385234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"6","issue":"4","first_page":"1","last_page":"23"},"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":0.9983000159263611,"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":0.9947999715805054,"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":0.8955779075622559},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.8368823528289795},{"id":"https://openalex.org/keywords/processor-register","display_name":"Processor register","score":0.7213183641433716},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7150028347969055},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5501530766487122},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4999661445617676},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4937938153743744},{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.48862653970718384},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.47457006573677063},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4606030583381653},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.44976741075515747},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4196937084197998},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3531373143196106},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34354883432388306},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.23415106534957886},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.21028980612754822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8955779075622559},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.8368823528289795},{"id":"https://openalex.org/C2871975","wikidata":"https://www.wikidata.org/wiki/Q187466","display_name":"Processor register","level":4,"score":0.7213183641433716},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7150028347969055},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5501530766487122},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4999661445617676},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4937938153743744},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.48862653970718384},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.47457006573677063},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4606030583381653},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.44976741075515747},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4196937084197998},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3531373143196106},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34354883432388306},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.23415106534957886},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.21028980612754822},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1596510.1596511","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1596510.1596511","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1596510.1596511","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.370.9874","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.370.9874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/tjones1/jones09-taco2.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/1596510.1596511","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1596510.1596511","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1596510.1596511","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.9200000166893005,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3649501416","display_name":null,"funder_award_id":"2009 SGR 1250","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G6866121486","display_name":null,"funder_award_id":"TIN2007-61763","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2148060071.pdf","grobid_xml":"https://content.openalex.org/works/W2148060071.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1549770887","https://openalex.org/W1868432933","https://openalex.org/W2032094184","https://openalex.org/W2034919323","https://openalex.org/W2080732703","https://openalex.org/W2089363288","https://openalex.org/W2089854225","https://openalex.org/W2096456916","https://openalex.org/W2097988171","https://openalex.org/W2102727118","https://openalex.org/W2108449262","https://openalex.org/W2108616660","https://openalex.org/W2110263160","https://openalex.org/W2111948219","https://openalex.org/W2117877698","https://openalex.org/W2118532220","https://openalex.org/W2122697795","https://openalex.org/W2129760904","https://openalex.org/W2133393645","https://openalex.org/W2137860371","https://openalex.org/W2138777150","https://openalex.org/W2141799201","https://openalex.org/W2145462867","https://openalex.org/W2153456949","https://openalex.org/W2156174665","https://openalex.org/W2159254447","https://openalex.org/W2164474450","https://openalex.org/W2168910052","https://openalex.org/W2171065098","https://openalex.org/W2543171663","https://openalex.org/W4250089307","https://openalex.org/W4251099593"],"related_works":["https://openalex.org/W3041671716","https://openalex.org/W2039534605","https://openalex.org/W2128881050","https://openalex.org/W2469267785","https://openalex.org/W2592314492","https://openalex.org/W1579918296","https://openalex.org/W3133724979","https://openalex.org/W2148060071","https://openalex.org/W2884390493","https://openalex.org/W4297236916"],"abstract_inverted_index":{"The":[0],"register":[1,68,104,108,115,150,188,193],"file":[2],"is":[3],"a":[4,8,56,65,96,107,136,153,178],"critical":[5],"component":[6],"in":[7,135],"modern":[9],"superscalar":[10],"processor.":[11],"It":[12,25],"must":[13,26,77],"be":[14,78],"large":[15],"enough":[16,29],"to":[17,31,73,102,112,129,141],"accommodate":[18],"the":[19,48,53,71,85,130,144,149,161,165],"results":[20],"of":[21,37,47,99,155,175,181,187],"all":[22],"in-flight":[23],"instructions.":[24],"also":[27],"have":[28],"ports":[30,163,196],"allow":[32],"simultaneous":[33],"issue":[34],"and":[35,75,119,157,159,201],"writeback":[36],"many":[38],"values":[39],"each":[40],"cycle.":[41],"However,":[42],"this":[43,125],"makes":[44],"it":[45],"one":[46],"most":[49,145],"energy-consuming":[50],"structures":[51],"within":[52],"processor":[54,131],"with":[55,177],"high":[57],"access":[58],"latency.":[59],"As":[60],"technology":[61],"scales,":[62],"there":[63],"comes":[64],"point":[66],"where":[67],"accesses":[69],"are":[70],"bottleneck":[72],"performance":[74,118,179,199],"so":[76],"pipelined":[79],"over":[80,152],"several":[81],"cycles.":[82],"This":[83],"increases":[84],"pipeline":[86],"depth,":[87],"lowering":[88],"performance.":[89],"To":[90],"overcome":[91],"these":[92],"challenges,":[93],"we":[94],"propose":[95],"novel":[97],"use":[98],"compiler":[100],"analysis":[101],"aid":[103],"caching.":[105],"Adding":[106],"cache":[109,142,151,194],"allows":[110],"us":[111,140],"preserve":[113],"single-cycle":[114],"accesses,":[116],"maintaining":[117],"reducing":[120],"energy":[121,202],"consumption.":[122],"We":[123],"do":[124],"by":[126],"passing":[127],"information":[128],"using":[132],"free":[133],"bits":[134],"real":[137],"ISA,":[138],"allowing":[139],"only":[143],"important":[146],"registers.":[147],"Evaluating":[148],"variety":[154],"sizes":[156],"associativities":[158],"varying":[160],"read":[162,195],"into":[164],"cache,":[166],"our":[167],"best":[168],"scheme":[169],"achieves":[170],"an":[171],"energy-delay-squared":[172],"(EDD)":[173],"product":[174],"0.81,":[176],"increase":[180],"11%.":[182],"Another":[183],"configuration":[184],"saves":[185],"13%":[186],"system":[189],"energy.":[190],"Using":[191],"four":[192],"brings":[197],"both":[198],"gains":[200],"savings,":[203],"consistently":[204],"outperforming":[205],"two":[206],"state-of-the-art":[207],"hardware":[208],"approaches.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
