{"id":"https://openalex.org/W4392504952","doi":"https://doi.org/10.1145/3649169.3649249","title":"Automatic Static Analysis-Guided Optimization of CUDA Kernels","display_name":"Automatic Static Analysis-Guided Optimization of CUDA Kernels","publication_year":2024,"publication_date":"2024-03-03","ids":{"openalex":"https://openalex.org/W4392504952","doi":"https://doi.org/10.1145/3649169.3649249"},"language":"en","primary_location":{"id":"doi:10.1145/3649169.3649249","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649169.3649249","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649169.3649249","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3649169.3649249","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094079611","display_name":"Mark Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark Lou","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009393339","display_name":"Stefan K. Muller","orcid":"https://orcid.org/0000-0002-3210-9727"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan K. Muller","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5094079611"],"corresponding_institution_ids":["https://openalex.org/I180949307"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01917569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9894000291824341,"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":0.9894000291824341,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/cuda","display_name":"CUDA","score":0.8504536151885986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7350714802742004},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5222121477127075}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8504536151885986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350714802742004},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5222121477127075}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649169.3649249","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649169.3649249","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649169.3649249","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3649169.3649249","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649169.3649249","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649169.3649249","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G1467667629","display_name":"SHF: Small: Automatic Qualitative and Quantitative Verification of CUDA Code","funder_award_id":"2007784","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8701372919","display_name":null,"funder_award_id":"CCF-2007784","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392504952.pdf","grobid_xml":"https://content.openalex.org/works/W4392504952.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1664545926","https://openalex.org/W1863336885","https://openalex.org/W1997614470","https://openalex.org/W2132117096","https://openalex.org/W2167675119","https://openalex.org/W2293015622","https://openalex.org/W2730174870","https://openalex.org/W2768683713","https://openalex.org/W3115175310","https://openalex.org/W3115446638","https://openalex.org/W3213748123","https://openalex.org/W4302306191"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3062287","https://openalex.org/W3213381848","https://openalex.org/W2005148983","https://openalex.org/W2017587301","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W2939411666","https://openalex.org/W2009169896"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,46,94,105,110,125],"framework":[3,23],"for":[4,24,42,68,130,164],"using":[5,155],"static":[6,47,60,126,156],"resource":[7,127],"analysis":[8,48,128,157],"to":[9,34,64,75,85],"guide":[10],"the":[11,35,51,140,152],"automatic":[12],"optimization":[13],"of":[14,54,59,82,96,119,124,142,154,160],"general-purpose":[15],"GPU":[16,55,71,165],"(GPGPU)":[17],"kernels":[18,39,144],"written":[19],"in":[20,62,109,147],"CUDA,":[21],"NVIDIA's":[22],"GPGPU":[25],"programming.":[26],"In":[27],"our":[28],"proposed":[29],"framework,":[30],"optimizations":[31,78,103],"are":[32,40],"applied":[33],"kernel":[36],"and":[37,104,150],"candidate":[38],"evaluated":[41],"performance":[43,69,91,141,162],"by":[44,145],"running":[45],"that":[49,79],"predicts":[50],"execution":[52],"cost":[53],"kernels.":[56,166],"The":[57,135],"use":[58,123],"analysis,":[61],"contrast":[63],"many":[65],"existing":[66],"frameworks":[67],"tuning":[70,163],"kernels,":[72],"lends":[73],"itself":[74],"high-level,":[76],"hardware-independent":[77],"can":[80],"be":[81],"particular":[83],"benefit":[84],"novice":[86],"programmers":[87],"unfamiliar":[88],"with":[89],"CUDA's":[90],"pitfalls.":[92],"As":[93],"proof":[95],"concept,":[97],"we":[98],"have":[99],"implemented":[100],"two":[101],"example":[102],"simple":[106],"search":[107],"strategy":[108],"tool":[111,129,137],"called":[112],"COpPER":[113],"(CUDA":[114],"Optimization":[115],"through":[116],"Programmatic":[117],"Estimation":[118],"Resources),":[120],"which":[121],"makes":[122],"CUDA":[131],"from":[132],"prior":[133],"work.":[134],"prototype":[136],"automatically":[138],"improves":[139],"sample":[143],"2-4%":[146],"initial":[148],"experiments,":[149],"demonstrates":[151],"feasibility":[153],"as":[158],"part":[159],"automated":[161]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}