{"id":"https://openalex.org/W2170881177","doi":"https://doi.org/10.1145/2540708.2540711","title":"SAGE","display_name":"SAGE","publication_year":2013,"publication_date":"2013-12-07","ids":{"openalex":"https://openalex.org/W2170881177","doi":"https://doi.org/10.1145/2540708.2540711","mag":"2170881177"},"language":"en","primary_location":{"id":"doi:10.1145/2540708.2540711","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2540708.2540711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th Annual IEEE/ACM 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/A5058642630","display_name":"Mehrzad Samadi","orcid":"https://orcid.org/0000-0002-3581-1255"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehrzad Samadi","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065946847","display_name":"Janghaeng Lee","orcid":"https://orcid.org/0009-0005-1915-6077"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Janghaeng Lee","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065079006","display_name":"D. Anoushe Jamshidi","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Anoushe Jamshidi","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071212745","display_name":"Amir Hormati","orcid":"https://orcid.org/0009-0002-5786-3301"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Hormati","raw_affiliation_strings":["Google Inc., Seattle, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Seattle, WA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mahlke","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.9231,"has_fulltext":false,"cited_by_count":254,"citation_normalized_percentile":{"value":0.9958332,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9991999864578247,"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/speedup","display_name":"Speedup","score":0.8689574003219604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.84792560338974},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7111278772354126},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.668501615524292},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6320222616195679},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5698264837265015},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5442978143692017},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5098268389701843},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.506946325302124},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5056073665618896},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.4889794588088989},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4365101456642151},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3923700451850891},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30348140001296997},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.17898434400558472},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10962745547294617},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09426328539848328}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8689574003219604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84792560338974},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7111278772354126},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.668501615524292},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6320222616195679},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5698264837265015},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5442978143692017},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5098268389701843},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.506946325302124},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5056073665618896},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.4889794588088989},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4365101456642151},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3923700451850891},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30348140001296997},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.17898434400558472},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10962745547294617},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09426328539848328},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2540708.2540711","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2540708.2540711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6368823070","display_name":null,"funder_award_id":"CNS-0964478, CCF-0916689","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G6462825679","display_name":null,"funder_award_id":"CNS-0964478, CCF-0916689","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1492552760","https://openalex.org/W1502558230","https://openalex.org/W1517684295","https://openalex.org/W1981473264","https://openalex.org/W1982401581","https://openalex.org/W2000873501","https://openalex.org/W2001784723","https://openalex.org/W2014620461","https://openalex.org/W2094190665","https://openalex.org/W2111444234","https://openalex.org/W2114703523","https://openalex.org/W2118190603","https://openalex.org/W2119299853","https://openalex.org/W2122410182","https://openalex.org/W2123468241","https://openalex.org/W2126869140","https://openalex.org/W2136944230","https://openalex.org/W2142883190","https://openalex.org/W2143283746","https://openalex.org/W2146065717","https://openalex.org/W2156180003","https://openalex.org/W2159350554","https://openalex.org/W2159992248","https://openalex.org/W2161907179","https://openalex.org/W2165448367","https://openalex.org/W2187230075","https://openalex.org/W2240938131","https://openalex.org/W2604272474","https://openalex.org/W3120740533","https://openalex.org/W3146354115","https://openalex.org/W3182211633","https://openalex.org/W4240237526","https://openalex.org/W4254896685","https://openalex.org/W6677939283","https://openalex.org/W6678087030","https://openalex.org/W6683537246"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Approximate":[0],"computing,":[1],"where":[2],"computation":[3],"accuracy":[4],"is":[5,15,43,79],"traded":[6],"off":[7],"for":[8],"better":[9],"performance":[10,86],"or":[11],"higher":[12],"data":[13,21,165],"throughput,":[14],"one":[16],"solution":[17],"that":[18,60,92,106,123,155],"can":[19,63,93],"help":[20],"processing":[22,178],"keep":[23],"pace":[24],"with":[25,96,114,119,188],"the":[26,68,73,80,127,142,157,196],"current":[27],"and":[28,39,57,88,167,176],"growing":[29],"overabundance":[30],"of":[31,83,111,117,162,173,185],"information.":[32],"For":[33],"particular":[34],"domains":[35],"such":[36],"as":[37],"multimedia":[38],"learning":[40,175],"algorithms,":[41],"approximation":[42,56,69,118,181],"commonly":[44],"used":[45],"today.":[46],"We":[47],"consider":[48],"automation":[49],"to":[50,53,71,130,135,151,195],"be":[51,64,94],"essential":[52],"provide":[54],"transparent":[55],"we":[58],"show":[59],"larger":[61],"benefits":[62],"achieved":[65],"by":[66,141],"constructing":[67],"techniques":[70,150],"fit":[72],"underlying":[74],"hardware.":[75],"Our":[76,99],"target":[77,137],"platform":[78],"GPU":[81,158],"because":[82],"its":[84],"high":[85],"capabilities":[87],"difficult":[89],"programming":[90],"challenges":[91],"alleviated":[95],"proper":[97],"automation.":[98],"approach,":[100],"SAGE,":[101],"combines":[102],"a":[103,109,120,136,171,200],"static":[104],"compiler":[105,146],"automatically":[107],"generates":[108],"set":[110,140,172],"CUDA":[112],"kernels":[113,129,154],"varying":[115],"levels":[116],"run-time":[121],"system":[122],"iteratively":[124],"selects":[125],"among":[126],"available":[128],"achieve":[131],"speedup":[132,187],"while":[133],"adhering":[134],"output":[138],"quality":[139,192],"user.":[143],"The":[144],"SAGE":[145],"employs":[147],"three":[148],"optimization":[149],"generate":[152],"approximate":[153],"exploit":[156],"microarchitecture:":[159],"selective":[160],"discarding":[161],"atomic":[163],"operations,":[164],"packing,":[166],"thread":[168],"fusion.":[169],"Across":[170],"machine":[174],"image":[177],"kernels,":[179],"SAGE's":[180],"yields":[182],"an":[183],"average":[184],"2.5x":[186],"less":[189],"than":[190],"10%":[191],"loss":[193],"compared":[194],"accurate":[197],"execution":[198],"on":[199],"NVIDIA":[201],"GTX":[202],"560":[203],"GPU.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":37},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":38},{"year":2015,"cited_by_count":32},{"year":2014,"cited_by_count":13}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}
