{"id":"https://openalex.org/W2156540297","doi":"https://doi.org/10.1177/1094342011434814","title":"Characterization and transformation of unstructured control flow in bulk synchronous GPU applications","display_name":"Characterization and transformation of unstructured control flow in bulk synchronous GPU applications","publication_year":2012,"publication_date":"2012-02-09","ids":{"openalex":"https://openalex.org/W2156540297","doi":"https://doi.org/10.1177/1094342011434814","mag":"2156540297"},"language":"en","primary_location":{"id":"doi:10.1177/1094342011434814","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342011434814","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-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/A5003741499","display_name":"Haicheng Wu","orcid":"https://orcid.org/0000-0003-0357-9049"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haicheng Wu","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006631932","display_name":"Gregory Diamos","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Diamos","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718193","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0001-8126-0370"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391324","display_name":"Si Li","orcid":"https://orcid.org/0000-0002-6631-7903"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Si Li","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111855694","display_name":"Sudhakar Yalamanchili","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudhakar Yalamanchili","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5149,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93010218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":"2","first_page":"170","last_page":"185"},"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":0.9966999888420105,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9958000183105469,"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/computer-science","display_name":"Computer science","score":0.8754501342773438},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8203561305999756},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8155679702758789},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.7881472110748291},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6241362690925598},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6026922464370728},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.49668437242507935},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.4636363387107849},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.42070746421813965},{"id":"https://openalex.org/keywords/flow-control","display_name":"Flow control (data)","score":0.4179513156414032},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3439081311225891},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18203780055046082},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1655421257019043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8754501342773438},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8203561305999756},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8155679702758789},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.7881472110748291},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6241362690925598},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6026922464370728},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.49668437242507935},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4636363387107849},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.42070746421813965},{"id":"https://openalex.org/C186766456","wikidata":"https://www.wikidata.org/wiki/Q612457","display_name":"Flow control (data)","level":2,"score":0.4179513156414032},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3439081311225891},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18203780055046082},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1655421257019043},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342011434814","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342011434814","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W65132813","https://openalex.org/W156943659","https://openalex.org/W2050513283","https://openalex.org/W2055881261","https://openalex.org/W2078983643","https://openalex.org/W2080592089","https://openalex.org/W2094752275","https://openalex.org/W2097561580","https://openalex.org/W2100403123","https://openalex.org/W2114067856","https://openalex.org/W2128046183","https://openalex.org/W2135947393","https://openalex.org/W2144344516","https://openalex.org/W2149693551","https://openalex.org/W2150566739","https://openalex.org/W2153185479","https://openalex.org/W2155568054","https://openalex.org/W2160428323","https://openalex.org/W2166163757","https://openalex.org/W2169880332","https://openalex.org/W2170879098","https://openalex.org/W2914237411","https://openalex.org/W2917160644","https://openalex.org/W3009973454","https://openalex.org/W4232955467","https://openalex.org/W4236485791","https://openalex.org/W4242961396","https://openalex.org/W4300490202"],"related_works":["https://openalex.org/W2794923745","https://openalex.org/W2075046026","https://openalex.org/W2008426882","https://openalex.org/W2340937903","https://openalex.org/W2119534391","https://openalex.org/W2146871484","https://openalex.org/W2128766769","https://openalex.org/W2244400696","https://openalex.org/W2182505841","https://openalex.org/W2156540297"],"abstract_inverted_index":{"In":[0],"this":[1,91],"paper":[2],"we":[3],"identify":[4],"important":[5,166],"classes":[6],"of":[7,71,90,113,123,171],"program":[8],"control":[9,38,57,65,74,81,97,130,150,161],"flows":[10],"in":[11,25,33,58,140],"applications":[12,62,115,172],"targeted":[13],"to":[14,86,145],"commercially":[15],"available":[16],"graphics":[17],"processing":[18],"units":[19],"(GPUs)":[20],"and":[21,35,77,105],"characterize":[22],"their":[23],"presence":[24],"real":[26],"workloads":[27],"such":[28],"as":[29,43],"those":[30],"that":[31,50,156],"occur":[32],"CUDA":[34,101],"OpenCL.":[36],"Broadly,":[37],"flow":[39,66,75,82,98,131,151],"can":[40,136],"be":[41,138],"characterized":[42],"structured":[44,64],"or":[45],"unstructured.":[46],"It":[47],"is":[48,93,103,116,164],"shown":[49],"most":[51],"existing":[52],"techniques":[53],"for":[54,100,126,168],"handling":[55],"divergent":[56],"bulk":[59],"synchronous":[60],"GPU":[61,114,154,174],"handle":[63],"efficiently,":[67],"some":[68],"are":[69],"incapable":[70],"executing":[72],"unstructured":[73,80,129,149,160],"directly,":[76],"none":[78],"handles":[79],"efficiently.":[83],"An":[84,95],"approach":[85],"reduce":[87],"the":[88,121,153],"impact":[89,108],"problem":[92],"provided.":[94],"unstructured-to-structured":[96],"transformation":[99,135],"kernels":[102],"implemented":[104],"its":[106],"performance":[107],"on":[109,132,152],"a":[110,141],"large":[111],"class":[112],"assessed.":[117],"The":[118,134],"results":[119],"quantify":[120],"importance":[122],"improving":[124],"support":[125,159],"programs":[127,147],"with":[128,148],"GPUs.":[133],"also":[137],"used":[139],"JIT":[142],"compiler":[143],"pass":[144],"execute":[146],"devices":[155],"do":[157],"not":[158],"flow.":[162],"This":[163],"an":[165],"capability":[167],"execution":[169],"portability":[170],"using":[173],"accelerators.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}