{"id":"https://openalex.org/W2083986745","doi":"https://doi.org/10.1145/2631913","title":"Scaling Performance via Self-Tuning Approximation for Graphics Engines","display_name":"Scaling Performance via Self-Tuning Approximation for Graphics Engines","publication_year":2014,"publication_date":"2014-08-29","ids":{"openalex":"https://openalex.org/W2083986745","doi":"https://doi.org/10.1145/2631913","mag":"2083986745"},"language":"en","primary_location":{"id":"doi:10.1145/2631913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2631913","pdf_url":null,"source":{"id":"https://openalex.org/S193109227","display_name":"ACM Transactions on Computer Systems","issn_l":"0734-2071","issn":["0734-2071","1557-7333"],"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 Computer Systems","raw_type":"journal-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, MI","University of Michigan, MI;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, 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, MI","University of Michigan, MI;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, 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, MI","University of Michigan, MI;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, MI;","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","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, MI","University of Michigan, MI;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, MI;","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6216,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7387707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"32","issue":"3","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9995999932289124,"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":0.9995999932289124,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9995999932289124,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8820751905441284},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8464075922966003},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6928977370262146},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5835675001144409},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.567279577255249},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5672566294670105},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5459035038948059},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5087404847145081},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.49038267135620117},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4870896339416504},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.46329817175865173},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.43629974126815796},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.41441136598587036},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36276131868362427},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28460046648979187},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0899299681186676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8820751905441284},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8464075922966003},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6928977370262146},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5835675001144409},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.567279577255249},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5672566294670105},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5459035038948059},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5087404847145081},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.49038267135620117},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4870896339416504},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.46329817175865173},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.43629974126815796},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.41441136598587036},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36276131868362427},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28460046648979187},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0899299681186676},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2631913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2631913","pdf_url":null,"source":{"id":"https://openalex.org/S193109227","display_name":"ACM Transactions on Computer Systems","issn_l":"0734-2071","issn":["0734-2071","1557-7333"],"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 Computer Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.501.1708","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.501.1708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cccp.eecs.umich.edu/papers/samadi-tocs14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4202251716","display_name":null,"funder_award_id":"CNS-0964478 and CCF-0916689","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G4701239277","display_name":null,"funder_award_id":"CNS-0964478 and CCF-0916689","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"}],"funders":[{"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/W2026764611","https://openalex.org/W2033982707","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/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/W2170881177","https://openalex.org/W2187230075","https://openalex.org/W2240938131","https://openalex.org/W2278668709","https://openalex.org/W2594947272","https://openalex.org/W2623293810","https://openalex.org/W2913668833","https://openalex.org/W3120740533","https://openalex.org/W3146354115","https://openalex.org/W3182211633"],"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":[13,21,163],"throughput,":[14],"one":[16],"solution":[17],"that":[18,60,92,104,121,153],"can":[19,63,93],"help":[20],"processing":[22,176],"keep":[23],"pace":[24],"with":[25,96,112,117,186],"the":[26,68,73,80,125,140,155,194],"current":[27],"and":[28,39,57,88,165,174],"growing":[29],"abundance":[30],"of":[31,83,109,115,160,171,183],"information.":[32],"For":[33],"particular":[34],"domains,":[35],"such":[36],"as":[37],"multimedia":[38],"learning":[40,173],"algorithms,":[41],"approximation":[42,69,116,179],"commonly":[44],"used":[45],"today.":[46],"We":[47],"consider":[48],"automation":[49],"to":[50,53,71,128,133,149,193],"be":[51,64,94],"essential":[52],"provide":[54],"transparent":[55],"approximation,":[56],"we":[58],"show":[59],"larger":[61],"benefits":[62],"achieved":[65],"by":[66,139],"constructing":[67],"techniques":[70,148],"fit":[72],"underlying":[74],"hardware.":[75],"Our":[76,99],"target":[77,135],"platform":[78],"GPU":[81,156],"because":[82],"its":[84],"high":[85],"capabilities":[87],"difficult":[89],"programming":[90],"challenges":[91],"alleviated":[95],"proper":[97],"automation.":[98],"approach\u2014SAGE\u2014combines":[100],"a":[101,107,118,134,169,198],"static":[102],"compiler":[103,144],"automatically":[105],"generates":[106],"set":[108,138,170],"CUDA":[110],"kernels":[111,127,152],"varying":[113],"levels":[114],"runtime":[119],"system":[120],"iteratively":[122],"selects":[123],"among":[124],"available":[126],"achieve":[129],"speedup":[130,185],"while":[131],"adhering":[132],"output":[136],"quality":[137,190],"user.":[141],"The":[142],"SAGE":[143],"employs":[145],"three":[146],"optimization":[147],"generate":[150],"approximate":[151],"exploit":[154],"microarchitecture:":[157],"selective":[158],"discarding":[159],"atomic":[161],"operations,":[162],"packing,":[164],"thread":[166],"fusion.":[167],"Across":[168],"machine":[172],"image":[175],"kernels,":[177],"SAGE's":[178],"yields":[180],"an":[181],"average":[182],"2.5\u00d7":[184],"less":[187],"than":[188],"10%":[189],"loss":[191],"compared":[192],"accurate":[195],"execution":[196],"on":[197],"NVIDIA":[199],"GTX":[200],"560":[201],"GPU.":[202]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}