{"id":"https://openalex.org/W3212980056","doi":"https://doi.org/10.1109/dac18074.2021.9586093","title":"ST<sup>2</sup> GPU: An Energy-Efficient GPU Design with Spatio-Temporal Shared-Thread Speculative Adders","display_name":"ST<sup>2</sup> GPU: An Energy-Efficient GPU Design with Spatio-Temporal Shared-Thread Speculative Adders","publication_year":2021,"publication_date":"2021-11-08","ids":{"openalex":"https://openalex.org/W3212980056","doi":"https://doi.org/10.1109/dac18074.2021.9586093","mag":"3212980056"},"language":"en","primary_location":{"id":"doi:10.1109/dac18074.2021.9586093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","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/A5034963609","display_name":"Vijay Kandiah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Vijay Kandiah","raw_affiliation_strings":["ECE, Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE, Northwestern University","institution_ids":["https://openalex.org/I4210100400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024167241","display_name":"Ali Murat Gok","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Murat Gok","raw_affiliation_strings":["Argonne National Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Labs","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054488954","display_name":"Georgios Tziantzioulis","orcid":"https://orcid.org/0000-0001-7614-3815"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgios Tziantzioulis","raw_affiliation_strings":["EE, Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EE, Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077219627","display_name":"Nikos Hardavellas","orcid":"https://orcid.org/0000-0002-1137-8100"},"institutions":[{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Nikos Hardavellas","raw_affiliation_strings":["CS & ECE, Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CS & ECE, Northwestern University","institution_ids":["https://openalex.org/I4210100400"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17595712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9986000061035156,"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/adder","display_name":"Adder","score":0.7977695465087891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767306923866272},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6946563720703125},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5524430274963379},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5145589709281921},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4638720750808716},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4416294991970062},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4161877930164337},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.34863170981407166},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18282097578048706},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.15455898642539978},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.13874024152755737},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1080540120601654},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08523029088973999}],"concepts":[{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.7977695465087891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767306923866272},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6946563720703125},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5524430274963379},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5145589709281921},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4638720750808716},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4416294991970062},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4161877930164337},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.34863170981407166},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18282097578048706},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.15455898642539978},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.13874024152755737},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1080540120601654},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08523029088973999},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac18074.2021.9586093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1607267489","https://openalex.org/W1976039195","https://openalex.org/W1979527452","https://openalex.org/W2014213913","https://openalex.org/W2045294186","https://openalex.org/W2077212538","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2152870706","https://openalex.org/W2155458498","https://openalex.org/W2157024459","https://openalex.org/W2273440736","https://openalex.org/W2614608740","https://openalex.org/W2769533663","https://openalex.org/W2941684109","https://openalex.org/W3147234326","https://openalex.org/W4250705145","https://openalex.org/W6669791407","https://openalex.org/W6694513646","https://openalex.org/W6746173537"],"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":{"Modern":[0],"GPUs":[1],"employ":[2,45],"thousands":[3],"of":[4,88,103],"cores,":[5],"yielding":[6],"higher":[7,11],"performance":[8,16,111],"but":[9],"also":[10],"power":[12,23,34,41],"consumption.":[13],"To":[14],"meet":[15],"targets":[17],"while":[18,85],"staying":[19],"within":[20],"a":[21,72],"reasonable":[22],"budget,":[24],"designers":[25],"have":[26],"to":[27,38,44],"make":[28],"these":[29],"execution":[30],"cores":[31],"increasingly":[32],"more":[33],"efficient.":[35],"One":[36],"way":[37],"increase":[39],"their":[40],"efficiency":[42],"is":[43],"power-efficient":[46],"adders.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"observe":[52],"that":[53,75,80,95],"consecutive":[54],"arithmetic":[55],"computations":[56],"from":[57],"the":[58,89,104],"same":[59],"code":[60],"location":[61],"are":[62],"highly":[63],"correlated":[64],"and":[65,112],"propose":[66],"ST":[67,96],"<sup":[68,97],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[69,98],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[70,99],"GPU,":[71],"GPU":[73,100,105],"architecture":[74],"uses":[76],"history-based":[77],"speculative":[78],"adders":[79],"produce":[81],"guaranteed":[82],"correct":[83],"results":[84],"saving":[86],"70%":[87],"nominal":[90],"adder":[91],"power.":[92],"We":[93],"estimate":[94],"saves":[101],"21%":[102],"chip":[106],"energy":[107],"with":[108],"practically":[109],"no":[110],"area":[113],"overheads.":[114]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}