{"id":"https://openalex.org/W2013959289","doi":"https://doi.org/10.1109/iccd.2014.6974700","title":"Accelerating divergent applications on SIMD architectures using neural networks","display_name":"Accelerating divergent applications on SIMD architectures using neural networks","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2013959289","doi":"https://doi.org/10.1109/iccd.2014.6974700","mag":"2013959289"},"language":"en","primary_location":{"id":"doi:10.1109/iccd.2014.6974700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2014.6974700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 32nd International Conference on Computer Design (ICCD)","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/A5059237344","display_name":"Beayna Grigorian","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Beayna Grigorian","raw_affiliation_strings":["Computer Science Department, UCLA, Los Angeles, USA","University of California, Los Angeles, Los Angeles, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, UCLA, Los Angeles, USA","institution_ids":[]},{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, United States","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083493225","display_name":"Glenn Reinman","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Glenn Reinman","raw_affiliation_strings":["Computer Science Department, UCLA, Los Angeles, USA","University of California, Los Angeles, Los Angeles, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, UCLA, Los Angeles, USA","institution_ids":[]},{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, United States","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059237344"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":2.1453,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.87138549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"68","issue":null,"first_page":"317","last_page":"323"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9973000288009644,"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":0.8328772783279419},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8117265701293945},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7298423647880554},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6647758483886719},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6473374366760254},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5843589305877686},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.5467339158058167},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.535763144493103},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4957226514816284},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4686262905597687},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4304690361022949},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3903893828392029},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.37101268768310547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2536035180091858},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20638874173164368},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12487003207206726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8328772783279419},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8117265701293945},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7298423647880554},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6647758483886719},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6473374366760254},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5843589305877686},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.5467339158058167},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.535763144493103},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4957226514816284},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4686262905597687},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4304690361022949},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3903893828392029},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.37101268768310547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2536035180091858},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20638874173164368},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12487003207206726},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccd.2014.6974700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2014.6974700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 32nd International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W164384110","https://openalex.org/W1498436455","https://openalex.org/W1981473264","https://openalex.org/W1988115241","https://openalex.org/W2042456747","https://openalex.org/W2068810256","https://openalex.org/W2089162427","https://openalex.org/W2090584832","https://openalex.org/W2105544671","https://openalex.org/W2120585153","https://openalex.org/W2124776405","https://openalex.org/W2128022558","https://openalex.org/W2128317332","https://openalex.org/W2135947393","https://openalex.org/W2138565468","https://openalex.org/W2142883190","https://openalex.org/W2155503253","https://openalex.org/W2155568054","https://openalex.org/W2156540297","https://openalex.org/W2156831150","https://openalex.org/W2160428323","https://openalex.org/W2169875292","https://openalex.org/W2187230075","https://openalex.org/W4234211448","https://openalex.org/W4236934668","https://openalex.org/W4240237526","https://openalex.org/W4253998042","https://openalex.org/W4299512035","https://openalex.org/W6675692759","https://openalex.org/W6678014108","https://openalex.org/W6678733365"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2028931088","https://openalex.org/W2069096825","https://openalex.org/W4248145683","https://openalex.org/W2107831078","https://openalex.org/W2100579514","https://openalex.org/W1979287416","https://openalex.org/W1672168401","https://openalex.org/W2798404616","https://openalex.org/W3013258932"],"abstract_inverted_index":{"In":[0],"this":[1,55],"work,":[2],"we":[3],"investigate":[4],"neural-network-based":[5],"solutions":[6],"to":[7,30,38],"the":[8,44,73],"well-known":[9],"problem":[10],"of":[11,92,97],"branch":[12,31],"divergence":[13],"in":[14],"Single":[15],"Instruction":[16],"Multiple":[17],"Data":[18],"(SIMD)":[19],"architectures.":[20],"Our":[21],"approach":[22,82],"isolates":[23],"code":[24],"regions":[25,45],"with":[26,46,99],"performance":[27,67,90],"degradation":[28],"due":[29],"divergence,":[32],"trains":[33],"neural":[34],"networks":[35],"(NNs)":[36],"offline":[37],"approximate":[39],"these":[40],"regions,":[41],"and":[42,68,79,94],"replaces":[43],"their":[47],"NN":[48],"approximations.":[49],"By":[50],"directly":[51],"manipulating":[52],"source":[53],"code,":[54],"platform-agnostic":[56],"methodology":[57],"translates":[58],"control":[59],"flow":[60],"into":[61],"non-divergent":[62],"computation,":[63],"trading-off":[64],"precision":[65],"for":[66],"energy":[69,95],"gains.":[70],"We":[71],"present":[72],"Neuralizer":[74],"(our":[75],"automated":[76],"software":[77],"flow),":[78],"evaluate":[80],"our":[81],"on":[83],"various":[84],"divergent":[85],"GPU":[86],"applications,":[87],"achieving":[88],"average":[89],"gains":[91],"13.6\u00d7":[93],"savings":[96],"14.8\u00d7":[98],"96%":[100],"accuracy.":[101]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}