{"id":"https://openalex.org/W2521014836","doi":"https://doi.org/10.1109/hpcsim.2016.7568315","title":"Efficient control flow restructuring for GPUs","display_name":"Efficient control flow restructuring for GPUs","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2521014836","doi":"https://doi.org/10.1109/hpcsim.2016.7568315","mag":"2521014836"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2016.7568315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2016.7568315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on High Performance Computing & Simulation (HPCS)","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/A5060097908","display_name":"Nico Rei\u00dfmann","orcid":"https://orcid.org/0000-0002-4096-1821"},"institutions":[{"id":"https://openalex.org/I4210165875","display_name":"NTNU Samfunnsforskning","ror":"https://ror.org/05pv30e80","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210165875"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Nico Reissmann","raw_affiliation_strings":["Dept. of Computer and Information Science, NTNU, Norway"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Science, NTNU, Norway","institution_ids":["https://openalex.org/I4210165875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033903615","display_name":"Thomas L. Falch","orcid":"https://orcid.org/0000-0001-8498-4825"},"institutions":[{"id":"https://openalex.org/I4210165875","display_name":"NTNU Samfunnsforskning","ror":"https://ror.org/05pv30e80","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210165875"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Thomas L. Falch","raw_affiliation_strings":["Dept. of Computer and Information Science, NTNU, Norway"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Science, NTNU, Norway","institution_ids":["https://openalex.org/I4210165875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051145355","display_name":"Benjamin Andreassen Bj\u00f8rnseth","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165875","display_name":"NTNU Samfunnsforskning","ror":"https://ror.org/05pv30e80","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210165875"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Benjamin A. Bjornseth","raw_affiliation_strings":["Dept. of Computer and Information Science, NTNU, Norway"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Science, NTNU, Norway","institution_ids":["https://openalex.org/I4210165875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054028290","display_name":"Helge Bahmann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Helge Bahmann","raw_affiliation_strings":["Google Z\u03cbrich"],"affiliations":[{"raw_affiliation_string":"Google Z\u03cbrich","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103526699","display_name":"Jan Christian Meyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165875","display_name":"NTNU Samfunnsforskning","ror":"https://ror.org/05pv30e80","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210165875"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Jan Christian Meyer","raw_affiliation_strings":["Dept. of Computer and Information Science, NTNU, Norway"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Science, NTNU, Norway","institution_ids":["https://openalex.org/I4210165875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067108530","display_name":"Magnus Jahre","orcid":"https://orcid.org/0000-0001-9147-5228"},"institutions":[{"id":"https://openalex.org/I4210165875","display_name":"NTNU Samfunnsforskning","ror":"https://ror.org/05pv30e80","country_code":"NO","type":"facility","lineage":["https://openalex.org/I4210165875"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Magnus Jahre","raw_affiliation_strings":["Dept. of Computer and Information Science, NTNU, Norway"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Science, NTNU, Norway","institution_ids":["https://openalex.org/I4210165875"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060097908"],"corresponding_institution_ids":["https://openalex.org/I4210165875"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.09695317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"57"},"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":0.9980000257492065,"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":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.886559247970581},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8274190425872803},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.7223386168479919},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6273516416549683},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6260873079299927},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6116225719451904},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.45700347423553467},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4487284719944},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.4237886965274811},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.41497477889060974},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.41012927889823914},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25361597537994385},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.11862853169441223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.886559247970581},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8274190425872803},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.7223386168479919},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6273516416549683},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6260873079299927},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6116225719451904},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.45700347423553467},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4487284719944},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.4237886965274811},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.41497477889060974},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.41012927889823914},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25361597537994385},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.11862853169441223},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcsim.2016.7568315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2016.7568315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on High Performance Computing & Simulation (HPCS)","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":29,"referenced_works":["https://openalex.org/W1491178396","https://openalex.org/W1721908487","https://openalex.org/W1954658694","https://openalex.org/W1963480348","https://openalex.org/W1968803687","https://openalex.org/W1970815868","https://openalex.org/W1972663160","https://openalex.org/W1981473264","https://openalex.org/W1994316441","https://openalex.org/W2012630996","https://openalex.org/W2026352419","https://openalex.org/W2080592089","https://openalex.org/W2083804777","https://openalex.org/W2094752275","https://openalex.org/W2100403123","https://openalex.org/W2114067856","https://openalex.org/W2118382442","https://openalex.org/W2128046183","https://openalex.org/W2128329055","https://openalex.org/W2135947393","https://openalex.org/W2156540297","https://openalex.org/W2160428323","https://openalex.org/W2167675119","https://openalex.org/W2168921806","https://openalex.org/W2169880332","https://openalex.org/W2182505841","https://openalex.org/W4242921921","https://openalex.org/W4249769983","https://openalex.org/W6685950538"],"related_works":["https://openalex.org/W2111180768","https://openalex.org/W2162270818","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"],"abstract_inverted_index":{"The":[0,68,206],"CUDA":[1,128],"and":[2,46,109,116,156,192],"OpenCL":[3],"programming":[4,14],"models":[5],"have":[6],"facilitated":[7],"the":[8,32,59,146,162,169,172,185,197],"widespread":[9],"adoption":[10],"of":[11,25,50,70,88,182,188,204,215],"general-purpose":[12],"GPU":[13],"for":[15,35,161,196],"data-parallel":[16],"applications.":[17],"GPUs":[18],"accelerate":[19],"these":[20],"applications":[21],"by":[22,57,118,201],"assigning":[23],"groups":[24],"threads":[26,37,43],"to":[27,76,100,126,130,184],"SIMD":[28],"units,":[29],"which":[30,97],"execute":[31],"same":[33],"instruction":[34],"all":[36,112],"in":[38,63,74,85,145,171,213],"a":[39,64,95,178,202],"group.":[40],"Individual":[41],"group":[42],"might":[44],"diverge":[45],"follow":[47],"different":[48],"paths":[49],"execution.":[51],"Divergent":[52],"branches":[53,78],"cause":[54],"performance":[55,66],"degradation":[56],"under-utilizing":[58],"execution":[60,87,155,159,186,194],"pipeline,":[61],"resulting":[62],"major":[65],"bottleneck.":[67],"presence":[69],"unstructured":[71,99,137,164,199],"control":[72,102,113,138,165],"flow":[73,114,139,166],"addition":[75],"divergent":[77],"causes":[79],"further":[80],"degradation,":[81],"since":[82],"it":[83,175],"results":[84],"repeated":[86],"instructions.":[89,216],"In":[90],"this":[91],"paper,":[92],"we":[93],"propose":[94],"transformation":[96,134],"converts":[98],"structured":[101,190],"flow.":[103],"It":[104],"only":[105,176,198],"creates":[106],"tail-controlled":[107],"loops,":[108],"properly":[110],"nests":[111],"splits":[115],"joins":[117],"inserting":[119],"predicates.":[120],"We":[121],"implement":[122],"an":[123],"additional":[124],"pass":[125],"NVIDIA's":[127],"compiler":[129],"experimentally":[131],"evaluate":[132],"our":[133],"using":[135],"synthetic":[136,163],"graphs,":[140],"as":[141,143],"well":[142],"kernels":[144,170],"Rodinia":[147],"benchmark":[148,173],"suite.":[149],"Our":[150],"approach":[151],"effectively":[152],"eliminates":[153],"redundant":[154],"potentially":[157],"improves":[158],"time":[160,187,195],"graphs.":[167],"For":[168],"suite,":[174],"adds":[177],"minor,":[179],"average":[180],"overhead":[181,208],"2.1%":[183],"already":[189],"kernels,":[191],"reduces":[193],"kernel":[200],"factor":[203],"five.":[205],"representational":[207],"at":[209],"compile-time":[210],"is":[211],"linear":[212],"terms":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}