{"id":"https://openalex.org/W4287079697","doi":"https://doi.org/10.48550/arxiv.2107.05681","title":"DARM: Control-Flow Melding for SIMT Thread Divergence Reduction -- Extended Version","display_name":"DARM: Control-Flow Melding for SIMT Thread Divergence Reduction -- Extended Version","publication_year":2021,"publication_date":"2021-07-12","ids":{"openalex":"https://openalex.org/W4287079697","doi":"https://doi.org/10.48550/arxiv.2107.05681"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2107.05681","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05681","pdf_url":"https://arxiv.org/pdf/2107.05681","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.05681","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005940767","display_name":"Charitha Saumya","orcid":"https://orcid.org/0000-0001-9900-2804","observed_orcids":["https://orcid.org/0000-0001-9900-2804"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saumya, Charitha","raw_affiliation_strings":["School of Electrical and Computer Engineering Purdue University West Lafayette , IN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering Purdue University West Lafayette , IN , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028997869","display_name":"Kirshanthan Sundararajah","orcid":"https://orcid.org/0000-0001-6384-062X","observed_orcids":["https://orcid.org/0000-0001-6384-062X"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sundararajah, Kirshanthan","raw_affiliation_strings":["School of Electrical and Computer Engineering Purdue University West Lafayette , IN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering Purdue University West Lafayette , IN , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075916086","display_name":"Milind Kulkarni","orcid":"https://orcid.org/0000-0001-6827-345X","observed_orcids":["https://orcid.org/0000-0001-6827-345X"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kulkarni, Milind","raw_affiliation_strings":["School of Electrical and Computer Engineering Purdue University West Lafayette , IN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering Purdue University West Lafayette , IN , USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/control-flow-divergence","display_name":"control flow divergence","score":0.9900000095367432},{"id":"https://openalex.org/keywords/simt","display_name":"SIMT","score":0.9020000100135803},{"id":"https://openalex.org/keywords/compiler-transformations","display_name":"compiler transformations","score":0.6610000133514404},{"id":"https://openalex.org/keywords/gpu-optimization","display_name":"GPU optimization","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7614811658859253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572155594825745},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.7183289527893066},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6596162915229797},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6326718330383301},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.462182879447937},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20069396495819092},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2107.05681","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05681","pdf_url":"https://arxiv.org/pdf/2107.05681","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2107.05681","doi":"https://doi.org/10.48550/arxiv.2107.05681","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.05681","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.05681","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05681","pdf_url":"https://arxiv.org/pdf/2107.05681","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2227270456","display_name":"SHF: Small: A Composable,  Sound Optimization Framework for Loops and Recursion","funder_award_id":"1908504","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8345018822","display_name":"SPX: Write Once, Run on Anything: Verified, Tuned Accelerator Kernels from High Level Specifications","funder_award_id":"1919197","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3096456556","https://openalex.org/W4240253816","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W2023832055","https://openalex.org/W2082485924","https://openalex.org/W2135947393","https://openalex.org/W3174544859","https://openalex.org/W3095167194"],"abstract_inverted_index":{"GPGPUs":[0],"use":[1],"the":[2,30,33,52,59,104,108,145],"Single-Instruction-Multiple-Thread":[3],"(SIMT)":[4],"execution":[5],"model":[6],"where":[7],"a":[8,20,23,36,91,123],"group":[9,21,31],"of":[10,51,90,107],"threads-wavefront":[11],"or":[12],"warp-execute":[13],"instructions":[14,86],"in":[15,19,29],"lockstep.":[16],"When":[17],"threads":[18,28,111],"encounter":[22],"branching":[24],"instruction,":[25],"not":[26],"all":[27],"take":[32],"same":[34],"path,":[35],"phenomenon":[37],"known":[38],"as":[39],"control-flow":[40,43,78,82,100,133,149],"divergence.":[41,116,150],"The":[42],"divergence":[44,79,101],"causes":[45],"performance":[46,146],"degradation":[47,147],"because":[48],"both":[49,88],"paths":[50],"branch":[53,109],"must":[54],"be":[55,96],"executed":[56],"one":[57],"after":[58],"other.":[60],"Prior":[61],"research":[62],"has":[63],"primarily":[64],"addressed":[65],"this":[66,118],"issue":[67],"through":[68],"architectural":[69],"modifications.":[70],"We":[71,139],"observe":[72],"that":[73,129,141],"certain":[74],"GPGPU":[75],"kernels":[76],"with":[77,84,135],"have":[80],"similar":[81,85,136],"structures":[83,134],"on":[87],"sides":[89,106],"branch.":[92],"This":[93],"structure":[94],"can":[95,130,143],"exploited":[97],"to":[98,112],"reduce":[99,144],"by":[102],"melding":[103],"two":[105],"allowing":[110],"reconverge":[113],"early,":[114],"reducing":[115],"In":[117],"work,":[119],"we":[120],"present":[121],"DARM,":[122],"compiler":[124],"analysis":[125],"and":[126],"transformation":[127],"framework":[128],"meld":[131],"divergent":[132],"instruction":[137],"sequences.":[138],"show":[140],"DARM":[142],"from":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-02T10:15:12.560889","created_date":"2022-07-25T00:00:00"}
