{"id":"https://openalex.org/W2025567168","doi":"https://doi.org/10.1145/2540708.2540716","title":"Exploiting GPU peak-power and performance tradeoffs through reduced effective pipeline latency","display_name":"Exploiting GPU peak-power and performance tradeoffs through reduced effective pipeline latency","publication_year":2013,"publication_date":"2013-12-07","ids":{"openalex":"https://openalex.org/W2025567168","doi":"https://doi.org/10.1145/2540708.2540716","mag":"2025567168"},"language":"en","primary_location":{"id":"doi:10.1145/2540708.2540716","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2540708.2540716","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/A5103414683","display_name":"Syed Zohaib Gilani","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Syed Zohaib Gilani","raw_affiliation_strings":["The University of Wisconsin--Madison","[Department of Electrical and Computer Engineering The University of Wisconsin-Madison]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Wisconsin--Madison","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering The University of Wisconsin-Madison]","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["The University of Wisconsin--Madison","[Department of Electrical and Computer Engineering The University of Wisconsin-Madison]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Wisconsin--Madison","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering The University of Wisconsin-Madison]","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103196891","display_name":"Michael Schulte","orcid":"https://orcid.org/0000-0003-1305-406X"},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michael J. Schulte","raw_affiliation_strings":["AMD Research, Advanced Micro Devices, Inc","AMD Research, Advanced Micro Devices, Inc.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD Research, Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]},{"raw_affiliation_string":"AMD Research, Advanced Micro Devices, Inc.#TAB#","institution_ids":["https://openalex.org/I1311921367"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5858,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83284533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"85"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994999766349792,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.8788903951644897},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.6122175455093384},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5878689289093018},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5810229182243347},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5584897398948669},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5557270050048828},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5341975092887878},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5012543201446533},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.49286890029907227},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.42982128262519836},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.3190385103225708},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24696460366249084},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.22640040516853333},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1651204526424408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8788903951644897},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.6122175455093384},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5878689289093018},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5810229182243347},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5584897398948669},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5557270050048828},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5341975092887878},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5012543201446533},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49286890029907227},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.42982128262519836},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.3190385103225708},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24696460366249084},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.22640040516853333},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1651204526424408},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":1,"locations":[{"id":"doi:10.1145/2540708.2540716","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2540708.2540716","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":[{"display_name":"Decent work and economic growth","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G4042413544","display_name":null,"funder_award_id":"2080.001","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G6967472675","display_name":null,"funder_award_id":"CCF-095360, CCF-1016262, CNS-1217102","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G6974033267","display_name":null,"funder_award_id":"CCF-095360, CCF-1016262, CNS-1217102","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"},{"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":23,"referenced_works":["https://openalex.org/W13192532","https://openalex.org/W1482635212","https://openalex.org/W1979527452","https://openalex.org/W2022632182","https://openalex.org/W2030281207","https://openalex.org/W2033597569","https://openalex.org/W2080592089","https://openalex.org/W2082849465","https://openalex.org/W2090584832","https://openalex.org/W2093043622","https://openalex.org/W2096661534","https://openalex.org/W2098143668","https://openalex.org/W2098158887","https://openalex.org/W2109846948","https://openalex.org/W2110195531","https://openalex.org/W2121024086","https://openalex.org/W2123990034","https://openalex.org/W2141840788","https://openalex.org/W2153039279","https://openalex.org/W2153169188","https://openalex.org/W2156510636","https://openalex.org/W2170382128","https://openalex.org/W2916844179"],"related_works":["https://openalex.org/W2150450196","https://openalex.org/W4249967283","https://openalex.org/W1558769186","https://openalex.org/W2045555750","https://openalex.org/W4239584669","https://openalex.org/W2103261828","https://openalex.org/W4250432526","https://openalex.org/W788524553","https://openalex.org/W2101536355","https://openalex.org/W2009783759"],"abstract_inverted_index":{"Modern":[0],"GPUs":[1,45,228],"share":[2],"limited":[3],"hardware":[4],"resources,":[5],"such":[6,196],"as":[7,115],"register":[8],"files,":[9],"among":[10],"a":[11,116,129,159,186,190,197,239],"large":[12,191],"number":[13,143],"of":[14,42,102,144,164,193,219,244],"concurrently":[15],"executing":[16],"threads.":[17],"For":[18],"efficient":[19],"resource":[20],"sharing,":[21],"several":[22],"buffering":[23],"and":[24,107,141,155,166,170,178],"collision":[25],"avoidance":[26],"stages":[27,36],"are":[28,46,79],"inserted":[29],"in":[30,147],"the":[31,38,100,120,142,148,181,213,217,220,234],"GPU":[32,149,182],"pipeline.":[33],"These":[34],"additional":[35],"increase":[37],"read-after-write":[39],"(RAW)":[40],"latencies":[41,52,140],"instructions.":[43,194],"Since":[44],"often":[47],"architected":[48],"to":[49,81,84,119,135,183,229],"hide":[50,85],"RAW":[51,87,139],"through":[53],"extensive":[54],"multithreading,":[55],"they":[56],"typically":[57],"do":[58,72],"not":[59,73],"employ":[60],"power-hungry":[61],"data-forwarding":[62],"networks":[63],"(DFNs).":[64],"However,":[65],"we":[66,92,127,199],"observe":[67],"that":[68,78,95,203],"many":[69,103],"GPGPU":[70,105,172,248],"applications":[71,106],"have":[74],"enough":[75],"active":[76],"threads":[77],"ready":[80],"issue":[82],"instructions":[83],"these":[86],"latencies.":[88],"In":[89],"this":[90],"paper,":[91],"first":[93],"demonstrate":[94],"DFNs":[96],"can":[97,204],"considerably":[98],"improve":[99],"performance":[101,162,214,242],"compute-intensive":[104],"then":[108],"propose":[109,200],"most":[110],"recent":[111],"result":[112],"forwarding":[113,221],"(MoRF)":[114],"low-power":[117,201],"alternative":[118],"DFN.":[121],"Second,":[122],"for":[123,168,189,246],"floating-point":[124],"(FP)":[125],"operations,":[126],"exploit":[128],"high-throughput":[130],"fused":[131],"multiply-add":[132],"(HFMA)":[133],"unit":[134],"further":[136],"reduce":[137,205],"both":[138,176],"FMA":[145],"units":[146],"without":[150,211],"impacting":[151],"instruction":[152],"throughput.":[153],"MoRF":[154,177],"HFMA":[156,179],"together":[157],"provide":[158],"geometric":[160,240],"mean":[161,241],"improvement":[163,243],"18%":[165],"29%":[167],"integer/single-precision":[169],"double-precision":[171,247],"applications,":[173],"respectively.":[174],"Finally,":[175],"allow":[180],"effectively":[184],"mimic":[185],"shallower":[187],"pipeline":[188],"percentage":[192],"Exploiting":[195],"benefit,":[198],"pipelines":[202],"peak":[206,224],"power":[207,225,236],"consumption":[208],"by":[209],"14%":[210],"affecting":[212],"or":[215],"increasing":[216],"complexity":[218],"network.":[222],"The":[223],"reduction":[226],"allows":[227],"operate":[230],"more":[231],"cores":[232],"within":[233],"same":[235],"budget,":[237],"achieving":[238],"33%":[245],"applications.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
