{"id":"https://openalex.org/W4397000568","doi":"https://doi.org/10.1109/coolchips61292.2024.10531165","title":"Branch Divergence-Aware Flexible Approximating Technique on GPUs","display_name":"Branch Divergence-Aware Flexible Approximating Technique on GPUs","publication_year":2024,"publication_date":"2024-04-17","ids":{"openalex":"https://openalex.org/W4397000568","doi":"https://doi.org/10.1109/coolchips61292.2024.10531165"},"language":"en","primary_location":{"id":"doi:10.1109/coolchips61292.2024.10531165","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/coolchips61292.2024.10531165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS)","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/A5046465633","display_name":"Reoma Matsuo","orcid":"https://orcid.org/0000-0002-7552-308X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Reoma Matsuo","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan","The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011897954","display_name":"Yuya Degawa","orcid":"https://orcid.org/0009-0001-2323-4569"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Degawa","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan","The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068571937","display_name":"Hidetsugu Irie","orcid":"https://orcid.org/0000-0002-5678-2377"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidetsugu Irie","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan","The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091236698","display_name":"Shuichi Sakai","orcid":"https://orcid.org/0000-0002-5471-9091"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuichi Sakai","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan","The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102797966","display_name":"Ryota Shioya","orcid":"https://orcid.org/0000-0002-9309-5875"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Shioya","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan","The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046465633"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.5198,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58330142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9997000098228455,"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/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/computer-science","display_name":"Computer science","score":0.8676936626434326},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6616125106811523},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6135735511779785},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5824311971664429},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5485341548919678},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.540216863155365},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5298659205436707},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.48948752880096436},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.423897922039032},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4126697778701782},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.41162562370300293},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.387717068195343},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2046765685081482},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12075963616371155},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0823608934879303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676936626434326},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6616125106811523},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6135735511779785},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5824311971664429},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5485341548919678},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.540216863155365},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5298659205436707},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.48948752880096436},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.423897922039032},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4126697778701782},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.41162562370300293},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.387717068195343},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2046765685081482},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12075963616371155},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0823608934879303},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coolchips61292.2024.10531165","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/coolchips61292.2024.10531165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1972563731","https://openalex.org/W1981473264","https://openalex.org/W1994316441","https://openalex.org/W2013247896","https://openalex.org/W2013959289","https://openalex.org/W2020073675","https://openalex.org/W2081373884","https://openalex.org/W2265166184","https://openalex.org/W2554131156","https://openalex.org/W2772152190","https://openalex.org/W3102510044","https://openalex.org/W4200592594","https://openalex.org/W4220858218","https://openalex.org/W4244316269","https://openalex.org/W6679076360"],"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":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4,54],"widely":[5],"adopted":[6],"in":[7,23,56,71,133],"various":[8],"fields,":[9],"attributed":[10],"to":[11,47,108,111,118],"their":[12,85],"high":[13],"throughput":[14],"and":[15,101,126],"energy":[16],"efficiency.":[17],"One":[18],"of":[19,79,99,104],"the":[20,36,77,97,102,121],"primary":[21],"challenges":[22],"GPU":[24],"computing":[25,69],"is":[26,30],"branch":[27],"divergence,":[28],"which":[29],"a":[31,57,66,91],"scenario":[32],"that":[33,94],"arises":[34],"when":[35],"control":[37],"flow":[38],"among":[39],"simultaneously":[40],"processing":[41],"threads":[42,53,81],"diverges.":[43],"This":[44,114],"phenomenon":[45],"leads":[46],"substantial":[48],"performance":[49],"degradation,":[50],"as":[51],"diverged":[52,80],"processed":[55],"time-slice":[58],"manner.":[59],"To":[60],"address":[61],"this":[62,88],"issue,":[63],"we":[64],"introduce":[65],"novel":[67],"approximate":[68],"approach":[70,89],"GPUs.":[72],"Our":[73],"proposed":[74],"method":[75,115],"approximates":[76],"outcomes":[78],"by":[82],"selectively":[83],"terminating":[84],"execution.":[86],"Additionally,":[87],"features":[90],"dynamic":[92],"mechanism":[93],"adjusts":[95],"both":[96],"likelihood":[98],"termination":[100],"number":[103],"instructions":[105],"executed":[106],"prior":[107],"termination,":[109],"according":[110],"user-defined":[112],"criteria.":[113],"enables":[116],"users":[117],"finely":[119],"tune":[120],"balance":[122],"between":[123],"execution":[124],"speed":[125],"result":[127],"fidelity,":[128],"thereby":[129],"providing":[130],"enhanced":[131],"flexibility":[132],"managing":[134],"computational":[135],"quality.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}