{"id":"https://openalex.org/W2005719980","doi":null,"title":"The Energy Impact of Aggressive Loop Fusion","display_name":"The Energy Impact of Aggressive Loop Fusion","publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W2005719980","mag":"2005719980"},"language":"en","primary_location":{"id":"pmh:oai:urresearch.rochester.edu:196","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1802/307","pdf_url":"https://urresearch.rochester.edu/fileDownloadForInstitutionalItem.action?itemId=196&itemFileId=279","source":{"id":"https://openalex.org/S4306400518","display_name":"UR Research (University of Rochester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5388228","host_organization_name":"University of Rochester","host_organization_lineage":["https://openalex.org/I5388228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"},"volume":null,"type":"report","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://urresearch.rochester.edu/fileDownloadForInstitutionalItem.action?itemId=196&itemFileId=279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076241682","display_name":"Yongkang Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongkang Zhu","raw_affiliation_strings":["[Dept. of Electr. & Comput. Eng., Rochester Univ., NY, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Dept. of Electr. & Comput. Eng., Rochester Univ., NY, USA]","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000686736","display_name":"Grigorios Magklis","orcid":null,"observed_orcids":[]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grigorios Magklis","raw_affiliation_strings":["Intel Barcelona Research Center, Barcelona, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Barcelona Research Center, Barcelona, Spain#TAB#","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079254515","display_name":"Michael Lee Scott","orcid":"https://orcid.org/0000-0001-8652-7644","observed_orcids":["https://orcid.org/0000-0001-8652-7644"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Scott","raw_affiliation_strings":["University of Rochester, New York;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester, New York;","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002777604","display_name":"Chen Ding","orcid":"https://orcid.org/0000-0003-4968-6659","observed_orcids":["https://orcid.org/0000-0003-4968-6659"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Ding","raw_affiliation_strings":["University of Rochester, New York;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester, New York;","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009386140","display_name":"David H. Albonesi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David H. Albonesi","raw_affiliation_strings":["University of Rochester, New York;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester, New York;","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.00019999999494757503,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/loop-fusion","display_name":"loop fusion","score":0.9929999709129333},{"id":"https://openalex.org/keywords/dynamic-power","display_name":"dynamic power","score":0.7400000095367432},{"id":"https://openalex.org/keywords/superscalar-processors","display_name":"superscalar processors","score":0.8169999718666077},{"id":"https://openalex.org/keywords/instruction-per-cycle","display_name":"instruction per cycle","score":0.578000009059906},{"id":"https://openalex.org/keywords/clock-domain-partitioning","display_name":"clock domain partitioning","score":0.5730000138282776},{"id":"https://openalex.org/keywords/dynamic-voltage-and-frequency-scaling","display_name":"dynamic voltage and frequency scaling","score":0.7509999871253967},{"id":"https://openalex.org/keywords/cache-reuse","display_name":"cache reuse","score":0.6489999890327454},{"id":"https://openalex.org/keywords/register-reuse","display_name":"register reuse","score":0.8140000104904175},{"id":"https://openalex.org/keywords/compiler-optimization","display_name":"compiler optimization","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6599007844924927},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.5468243956565857},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5435783863067627},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5282047390937805},{"id":"https://openalex.org/C168522837","wikidata":"https://www.wikidata.org/wiki/Q679552","display_name":"Branch predictor","level":2,"score":0.5105963349342346},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5103175044059753},{"id":"https://openalex.org/C134718785","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fission","level":3,"score":0.4894033968448639},{"id":"https://openalex.org/C178693496","wikidata":"https://www.wikidata.org/wiki/Q911691","display_name":"Clock rate","level":3,"score":0.45782172679901123},{"id":"https://openalex.org/C82653869","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fusion","level":3,"score":0.456904798746109},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4552052319049835},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.44799041748046875},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4206509590148926},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41724273562431335},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3724896311759949},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3611755073070526},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1442956030368805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1232408881187439},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10263624787330627},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08369114995002747},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:urresearch.rochester.edu:196","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1802/307","pdf_url":"https://urresearch.rochester.edu/fileDownloadForInstitutionalItem.action?itemId=196&itemFileId=279","source":{"id":"https://openalex.org/S4306400518","display_name":"UR Research (University of Rochester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5388228","host_organization_name":"University of Rochester","host_organization_lineage":["https://openalex.org/I5388228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.121.7808","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.121.7808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rochester.edu/~maglis/ftp/zhu_pact04_corrected.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.135.7502","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.7502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rochester.edu/u/scott/papers/2003_TR822.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.981","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rochester.edu/~cding/Documents/Publications/pact04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.8567","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.8567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.rochester.edu/~albonesi/research/papers/pact04.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:urresearch.rochester.edu:196","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1802/307","pdf_url":"https://urresearch.rochester.edu/fileDownloadForInstitutionalItem.action?itemId=196&itemFileId=279","source":{"id":"https://openalex.org/S4306400518","display_name":"UR Research (University of Rochester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5388228","host_organization_name":"University of Rochester","host_organization_lineage":["https://openalex.org/I5388228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8485000133514404,"display_name":"Affordable and clean energy"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1219830352","display_name":"Complexity-Adaptive Processors:  Dynamic IPC/Critical Path  Optimization","funder_award_id":"9811929","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1560258301","display_name":"High-Performance Synchronization for User-Level Applications","funder_award_id":"0204344","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1611343528","display_name":"CISE Research Infrastructure:  Spatial Intelligence for Computer-Enhanced Interaction with Physical Environments","funder_award_id":"0080124","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1769263893","display_name":"ITR:    Dynamically Tunable Clustered Multithreaded Architectures","funder_award_id":"0219848","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5190177696","display_name":"CAREER:  Compiler-Assisted Data Adaptation","funder_award_id":"0238176","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5382222432","display_name":"CAREER: Architectural Optimization of High Performance      Microprocessor-Based Systems","funder_award_id":"9701915","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G701811451","display_name":"Transparent Middleware Support for Shared State on Heterogeneous Clusters","funder_award_id":"9988361","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2005719980.pdf","grobid_xml":"https://content.openalex.org/works/W2005719980.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W346213406","https://openalex.org/W1494930385","https://openalex.org/W1536051636","https://openalex.org/W1551026808","https://openalex.org/W1560132800","https://openalex.org/W1580869290","https://openalex.org/W1587615044","https://openalex.org/W1780792251","https://openalex.org/W2011024076","https://openalex.org/W2025168586","https://openalex.org/W2030934436","https://openalex.org/W2032094184","https://openalex.org/W2032404709","https://openalex.org/W2038906116","https://openalex.org/W2048305092","https://openalex.org/W2080422774","https://openalex.org/W2082011829","https://openalex.org/W2099961254","https://openalex.org/W2100767055","https://openalex.org/W2102727118","https://openalex.org/W2108730429","https://openalex.org/W2121698147","https://openalex.org/W2129763083","https://openalex.org/W2131308327","https://openalex.org/W2132471117","https://openalex.org/W2133393645","https://openalex.org/W2138007781","https://openalex.org/W2144181355","https://openalex.org/W2149756939","https://openalex.org/W2160650521","https://openalex.org/W2163532955","https://openalex.org/W2172062522","https://openalex.org/W2244841219","https://openalex.org/W3125664926"],"related_works":["https://openalex.org/W2769070727","https://openalex.org/W2586845463","https://openalex.org/W2016344549","https://openalex.org/W2478648283","https://openalex.org/W1995604628","https://openalex.org/W7038377499","https://openalex.org/W2397792450","https://openalex.org/W2606745440","https://openalex.org/W1973346605","https://openalex.org/W1856606395"],"abstract_inverted_index":{"Loop":[0],"fusion":[1,39,131],"combines":[2],"corresponding":[3],"iterations":[4],"of":[5,47,113,121,130,148],"different":[6],"loops.":[7],"It":[8],"is":[9,85],"traditionally":[10],"used":[11],"to":[12,41,60,171,176,186,194],"decrease":[13],"program":[14,37,72,80,115],"run":[15,81,106,164],"time,":[16],"by":[17,89],"reducing":[18,90],"loop":[19],"overhead":[20],"and":[21,63,92,135,143,197],"increasing":[22],"data":[23],"locality.":[24],"In":[25,174],"this":[26],"paper,":[27],"however,":[28,88],"we":[29,156],"consider":[30],"its":[31],"effect":[32],"on":[33,94,133],"energy.":[34],"By":[35],"merging":[36],"phases,":[38],"tends":[40,59],"increase":[42,61],"the":[43,111,128,149,153,181,190],"uniformity,":[44],"or":[45],"balance":[46,58,116],"demand":[48],"for":[49],"system":[50],"resources.":[51],"On":[52],"a":[53,95,118,144],"conventional":[54],"superscalar":[55],"processor,":[56],"increased":[57,114],"IPC,":[62],"thus":[64],"dynamic":[65],"power,":[66],"so":[67],"that":[68,192],"fusion-induced":[69,195],"improvements":[70,78,102],"in":[71,79],"energy":[73,101,123,158,198],"are":[74],"slightly":[75],"smaller":[76],"than":[77],"time.":[82],"If":[83],"IPC":[84],"held":[86],"constant,":[87],"frequency":[91],"voltage\u2014particularly":[93],"processor":[96,122],"with":[97,163],"multiple":[98],"clock":[99],"domains\u2014then":[100],"may":[103],"significantly":[104],"exceed":[105],"time":[107,196],"improvements.":[108],"We":[109,125],"demonstrate":[110,157],"benefits":[112,129],"under":[117],"theoretical":[119,179],"model":[120],"consumption.":[124],"then":[126],"evaluate":[127],"empirically":[132],"synthetic":[134],"real-world":[136,154],"benchmarks,":[137,155],"using":[138],"our":[139,178],"existing":[140],"loop-fusing":[141],"compiler":[142],"heavily":[145],"modified":[146],"version":[147],"SimpleScalar/Wattch":[150],"simulator.":[151],"For":[152],"savings":[159],"ranging":[160,166],"from":[161,167],"7\u201340%,":[162],"times":[165],"1":[168],"%":[169],"slowdown":[170],"17%":[172],"speedup.":[173],"addition":[175],"validating":[177],"model,":[180],"simulation":[182],"results":[183],"allow":[184],"us":[185],"\u201ctease":[187],"apart":[188],"\u201d":[189],"factors":[191],"contribute":[193],"savings.":[199],"1.":[200]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}
