{"id":"https://openalex.org/W3146509083","doi":"https://doi.org/10.1109/isca.2012.6237006","title":"CAPRI: Prediction of compaction-adequacy for handling control-divergence in GPGPU architectures","display_name":"CAPRI: Prediction of compaction-adequacy for handling control-divergence in GPGPU architectures","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W3146509083","doi":"https://doi.org/10.1109/isca.2012.6237006","mag":"3146509083"},"language":"en","primary_location":{"id":"doi:10.1109/isca.2012.6237006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isca.2012.6237006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 39th Annual International Symposium on Computer Architecture (ISCA)","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/A5091648103","display_name":"Minsoo Rhu","orcid":"https://orcid.org/0000-0003-3303-8681"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minsoo Rhu","raw_affiliation_strings":["Electrical and Computer Engineering Department, The University of Texas at Austin, USA","Electrical and Computer Engineering Department, University of Texas, Austin, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, The University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Texas, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013680653","display_name":"Mattan Erez","orcid":"https://orcid.org/0000-0002-1567-4097"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mattan Erez","raw_affiliation_strings":["Electrical and Computer Engineering Department, The University of Texas at Austin, USA","Electrical and Computer Engineering Department, University of Texas, Austin, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, The University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Texas, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091648103"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":2.9277,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91362156,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"71"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9984999895095825,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8434929847717285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8393622040748596},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6586686372756958},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.6438848972320557},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6246945261955261},{"id":"https://openalex.org/keywords/control-unit","display_name":"Control unit","score":0.4609222412109375},{"id":"https://openalex.org/keywords/compaction","display_name":"Compaction","score":0.4543253481388092},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13675206899642944},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09783771634101868}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8434929847717285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8393622040748596},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6586686372756958},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.6438848972320557},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6246945261955261},{"id":"https://openalex.org/C81988521","wikidata":"https://www.wikidata.org/wiki/Q676838","display_name":"Control unit","level":2,"score":0.4609222412109375},{"id":"https://openalex.org/C196715460","wikidata":"https://www.wikidata.org/wiki/Q1414356","display_name":"Compaction","level":2,"score":0.4543253481388092},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13675206899642944},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09783771634101868},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/isca.2012.6237006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isca.2012.6237006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 39th Annual International Symposium on Computer Architecture (ISCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.649.3003","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.649.3003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lph.ece.utexas.edu/merez/uploads/MattanErez/capri_isca2012.pdf","raw_type":"text"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/43401","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/43401","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1504291959","https://openalex.org/W1979527452","https://openalex.org/W1990800384","https://openalex.org/W2040469876","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2097561580","https://openalex.org/W2114067856","https://openalex.org/W2120585153","https://openalex.org/W2135947393","https://openalex.org/W2140311411","https://openalex.org/W2144481293","https://openalex.org/W2145866640","https://openalex.org/W2154449573","https://openalex.org/W2155568054","https://openalex.org/W2156540297","https://openalex.org/W2156831150","https://openalex.org/W2160428323","https://openalex.org/W2166621589","https://openalex.org/W2169150396","https://openalex.org/W4245217677"],"related_works":["https://openalex.org/W3013719031","https://openalex.org/W3140187064","https://openalex.org/W2107831078","https://openalex.org/W4248145683","https://openalex.org/W2100579514","https://openalex.org/W1979287416","https://openalex.org/W1672168401","https://openalex.org/W2798404616","https://openalex.org/W3013258932","https://openalex.org/W3095167194"],"abstract_inverted_index":{"Wide":[0],"SIMD-based":[1],"GPUs":[2,16],"have":[3],"evolved":[4],"into":[5,83],"a":[6,40,84,91,134,149,162],"promising":[7],"platform":[8],"for":[9,169],"running":[10],"general":[11],"purpose":[12],"workloads.":[13],"Current":[14],"programmable":[15],"allow":[17],"even":[18],"code":[19],"with":[20],"irregular":[21],"control":[22,47],"to":[23,38,95,115,143],"execute":[24,39],"well":[25],"on":[26,123],"their":[27],"SIMD":[28,34,86],"pipelines.":[29],"To":[30],"do":[31],"this,":[32],"each":[33],"lane":[35],"is":[36,49,121],"considered":[37],"logical":[41],"thread":[42],"where":[43],"hardware":[44],"ensures":[45],"that":[46,98,108,112,140,157,179,187,194],"flow":[48],"accurate":[50],"by":[51,77,104],"automatically":[52],"applying":[53],"masked":[54,57,68],"execution.":[55],"The":[56],"execution,":[58],"however,":[59],"often":[60],"degrades":[61],"performance":[62,176],"because":[63],"the":[64,100,124,131,184],"issue":[65],"slots":[66],"of":[67,133,165],"lanes":[69],"are":[70,113,141],"wasted.":[71],"This":[72,88],"degradation":[73],"can":[74],"be":[75],"mitigated":[76],"dynamically":[78,129],"compacting":[79],"multiple":[80],"unmasked":[81],"threads":[82,111,139],"single":[85],"unit.":[87],"paper":[89],"proposes":[90],"fundamentally":[92],"new":[93],"approach":[94],"branch":[96,135],"compaction":[97,190],"avoids":[99],"unnecessary":[101],"synchronization":[102],"required":[103],"previous":[105],"techniques":[106],"and":[107,136,155,167,171,191],"only":[109,137],"stalls":[110,138,195],"likely":[114],"benefit":[116,144],"from":[117,145],"compaction.":[118,146],"Our":[119,175],"technique":[120],"based":[122],"compaction-adequacy":[125],"predictor":[126],"(CAPRI).":[127],"CAPRI":[128,180],"identifies":[130],"compaction-effectiveness":[132],"predicted":[142],"We":[147],"utilize":[148],"simple":[150,159],"single-level":[151],"branch-predictor":[152],"inspired":[153],"structure":[154],"show":[156],"this":[158],"configuration":[160],"attains":[161],"prediction":[163],"accuracy":[164],"99.8%":[166],"86.6%":[168],"non-divergent":[170],"divergent":[172,198],"workloads,":[173],"respectively.":[174],"evaluation":[177],"demonstrates":[178],"consistently":[181],"outperforms":[182],"both":[183],"baseline":[185],"design":[186],"never":[188],"attempts":[189],"prior":[192],"work":[193],"upon":[196],"all":[197],"branches.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}