{"id":"https://openalex.org/W2002991280","doi":"https://doi.org/10.1145/2629681","title":"Efficient Power Gating of SIMD Accelerators Through Dynamic Selective Devectorization in an HW/SW Codesigned Environment","display_name":"Efficient Power Gating of SIMD Accelerators Through Dynamic Selective Devectorization in an HW/SW Codesigned Environment","publication_year":2014,"publication_date":"2014-07-31","ids":{"openalex":"https://openalex.org/W2002991280","doi":"https://doi.org/10.1145/2629681","mag":"2002991280"},"language":"en","primary_location":{"id":"doi:10.1145/2629681","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2629681","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2629681","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/10.1145/2629681","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017675158","display_name":"Rakesh Kumar","orcid":"https://orcid.org/0000-0001-6306-304X"},"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":"Rakesh Kumar","raw_affiliation_strings":["Universitat Polit\u00e8cnica De Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica De Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731047","display_name":"A. Mart\u00ednez","orcid":"https://orcid.org/0000-0001-8292-0377"},"institutions":[{"id":"https://openalex.org/I4210136471","display_name":"FC Barcelona","ror":"https://ror.org/04bpz1v84","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210136471"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alejandro Mart\u00ednez","raw_affiliation_strings":["Intel Barcelona Research Center, Intel Labs, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Intel Barcelona Research Center, Intel Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I4210136471"]}]},{"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 Gonz\u00e1lez","raw_affiliation_strings":["Intel Barcelona Research Center, Intel Labs -- UPC, Barcelona, Spain","[Intel Barcelona Research Center, Intel Laboratories, UPC, Barcelona, Spain]"],"affiliations":[{"raw_affiliation_string":"Intel Barcelona Research Center, Intel Labs -- UPC, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"[Intel Barcelona Research Center, Intel Laboratories, UPC, Barcelona, Spain]","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017675158"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":1.2259,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.78357282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"11","issue":"3","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":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9980999827384949,"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/idle","display_name":"Idle","score":0.8544691205024719},{"id":"https://openalex.org/keywords/power-gating","display_name":"Power gating","score":0.8302973508834839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7866753339767456},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7173938751220703},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.5631808638572693},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5183930993080139},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.46311676502227783},{"id":"https://openalex.org/keywords/leakage-power","display_name":"Leakage power","score":0.4314620792865753},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.42418092489242554},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.41316795349121094},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.3693162202835083},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36671245098114014},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.21344810724258423},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15661197900772095},{"id":"https://openalex.org/keywords/transistor","display_name":"Transistor","score":0.1396627128124237},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13553357124328613},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11734998226165771},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07791632413864136}],"concepts":[{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.8544691205024719},{"id":"https://openalex.org/C2780700455","wikidata":"https://www.wikidata.org/wiki/Q7236515","display_name":"Power gating","level":4,"score":0.8302973508834839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7866753339767456},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7173938751220703},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.5631808638572693},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5183930993080139},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.46311676502227783},{"id":"https://openalex.org/C2987719587","wikidata":"https://www.wikidata.org/wiki/Q1811428","display_name":"Leakage power","level":4,"score":0.4314620792865753},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.42418092489242554},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.41316795349121094},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3693162202835083},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36671245098114014},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.21344810724258423},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15661197900772095},{"id":"https://openalex.org/C172385210","wikidata":"https://www.wikidata.org/wiki/Q5339","display_name":"Transistor","level":3,"score":0.1396627128124237},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13553357124328613},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11734998226165771},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07791632413864136},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2629681","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2629681","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2629681","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:pure.ed.ac.uk:openaire/03b126e4-5819-48b3-8c09-80101b3001f7","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/03b126e4-5819-48b3-8c09-80101b3001f7","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kumar, R, Mart\u00ednez, A & Gonz\u00e1lez, A 2014, 'Efficient Power Gating of SIMD Accelerators Through Dynamic Selective Devectorization in an HW/SW Codesigned Environment', ACM Transactions on Architecture and Code Optimization, vol. 11, no. 3, 25. https://doi.org/10.1145/2629681","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/03b126e4-5819-48b3-8c09-80101b3001f7","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/03b126e4-5819-48b3-8c09-80101b3001f7","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.1145/2629681","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2629681","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2629681","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2002991280.pdf","grobid_xml":"https://content.openalex.org/works/W2002991280.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1949737515","https://openalex.org/W1984972320","https://openalex.org/W2005343162","https://openalex.org/W2021688604","https://openalex.org/W2026686501","https://openalex.org/W2059807497","https://openalex.org/W2066397066","https://openalex.org/W2092721177","https://openalex.org/W2096335660","https://openalex.org/W2130123999","https://openalex.org/W2134633067","https://openalex.org/W2134663450","https://openalex.org/W2139542266","https://openalex.org/W2144726606","https://openalex.org/W2145071646","https://openalex.org/W2148865465","https://openalex.org/W2149959321","https://openalex.org/W2153478340","https://openalex.org/W2157074753","https://openalex.org/W2158899676","https://openalex.org/W2165581716","https://openalex.org/W2170382128","https://openalex.org/W4236971743","https://openalex.org/W4239813889","https://openalex.org/W4242764150","https://openalex.org/W4251914687","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3092821848","https://openalex.org/W2259094912","https://openalex.org/W3201504882","https://openalex.org/W2015140512","https://openalex.org/W2004834197","https://openalex.org/W2952738319","https://openalex.org/W1970386983","https://openalex.org/W2404323568","https://openalex.org/W2980874615","https://openalex.org/W2066397066"],"abstract_inverted_index":{"Leakage":[0],"energy":[1,70,155],"is":[2,38,72,130,141,184],"a":[3,18,99],"growing":[4],"concern":[5],"in":[6,33,98],"current":[7],"and":[8,164,173],"future":[9],"microprocessors.":[10],"Functional":[11],"units":[12,56],"of":[13,21,40,68,127,157],"microprocessors":[14],"are":[15,95,161],"responsible":[16],"for":[17,88,120,170],"major":[19],"fraction":[20],"this":[22],"energy.":[23,49],"Therefore,":[24,65],"reducing":[25],"functional":[26,55],"unit":[27],"leakage":[28,48,69],"has":[29],"received":[30],"much":[31],"attention":[32],"recent":[34],"years.":[35],"Power":[36,50],"gating":[37,51,169],"one":[39],"the":[41,54,58,63,66,76,85,89,105,112,124,128,134,144,153,158,179],"most":[42],"widely":[43],"used":[44],"techniques":[45],"to":[46,61,75,103,116,132],"minimize":[47],"turns":[52],"off":[53],"during":[57],"idle":[59,77,86],"periods":[60],"reduce":[62],"leakage.":[64],"amount":[67],"savings":[71,156],"directly":[73],"proportional":[74],"time":[78,122],"duration.":[79],"This":[80],"article":[81],"focuses":[82],"on":[83,119,143],"increasing":[84],"interval":[87],"higher":[90,106,113,135],"SIMD":[91,107,146],"lanes.":[92],"The":[93,138],"applications":[94],"profiled":[96],"dynamically,":[97],"hardware/software":[100],"codesigned":[101],"environment,":[102],"find":[104],"lanes'":[108],"usage":[109],"pattern.":[110],"If":[111],"lanes":[114,136],"need":[115],"be":[117],"turned":[118],"small":[121],"periods,":[123],"corresponding":[125],"portion":[126],"code":[129,140],"devectorized":[131,139],"keep":[133],"off.":[137],"executed":[142],"lowest":[145],"lane.":[147],"Our":[148],"experimental":[149],"results":[150],"show":[151],"that":[152],"average":[154],"proposed":[159],"mechanism":[160],"15%,":[162],"12%,":[163],"71%":[165],"greater":[166],"than":[167],"power":[168],"SPECFP2006,":[171],"Physicsbench,":[172],"Eigen":[174],"benchmark":[175],"suites,":[176],"respectively.":[177],"Moreover,":[178],"slowdown":[180],"caused":[181],"by":[182],"devectorization":[183],"negligible.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
