{"id":"https://openalex.org/W4255785636","doi":"https://doi.org/10.1109/cgo.2019.8661186","title":"Decoding CUDA Binary","display_name":"Decoding CUDA Binary","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W4255785636","doi":"https://doi.org/10.1109/cgo.2019.8661186"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2019.8661186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070117880","display_name":"Ari B. Hayes","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ari B. Hayes","raw_affiliation_strings":["Department of Computer Science, Rutgers University, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726358","display_name":"Fei Hua","orcid":"https://orcid.org/0000-0002-9355-2618"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Hua","raw_affiliation_strings":["Department of Computer Science, Rutgers University, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101465464","display_name":"Jin Huang","orcid":"https://orcid.org/0000-0002-7435-0391"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin Huang","raw_affiliation_strings":["Department of Computer Science, Rutgers University, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101418750","display_name":"Yanhao Chen","orcid":"https://orcid.org/0000-0002-6585-9110"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanhao Chen","raw_affiliation_strings":["Department of Computer Science, Rutgers University, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071204460","display_name":"Eddy Z. Zhang","orcid":"https://orcid.org/0000-0002-3815-4318"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eddy Z. Zhang","raw_affiliation_strings":["Department of Computer Science, Rutgers University, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"241"},"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":0.9987000226974487,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9966999888420105,"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":0.826502799987793},{"id":"https://openalex.org/keywords/binary-translation","display_name":"Binary translation","score":0.6596775650978088},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.656663179397583},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.6418631076812744},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6057658195495605},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5533341765403748},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5098787546157837},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5000863075256348},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4822000563144684},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4801616072654724},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4504257142543793},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.440733939409256},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4158395528793335},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41139304637908936},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.280628502368927},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11710524559020996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826502799987793},{"id":"https://openalex.org/C2778971978","wikidata":"https://www.wikidata.org/wiki/Q2287075","display_name":"Binary translation","level":3,"score":0.6596775650978088},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.656663179397583},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.6418631076812744},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6057658195495605},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5533341765403748},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5098787546157837},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5000863075256348},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4822000563144684},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4801616072654724},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4504257142543793},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.440733939409256},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4158395528793335},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41139304637908936},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.280628502368927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11710524559020996},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2019.8661186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1506474685","https://openalex.org/W1547658234","https://openalex.org/W1968197401","https://openalex.org/W1979527452","https://openalex.org/W2041356909","https://openalex.org/W2080592089","https://openalex.org/W2093843662","https://openalex.org/W2110195531","https://openalex.org/W2126830109","https://openalex.org/W2345717615","https://openalex.org/W2554796001","https://openalex.org/W2580538010","https://openalex.org/W2796649226","https://openalex.org/W3211116964","https://openalex.org/W4295827684","https://openalex.org/W6638906346","https://openalex.org/W6673829052","https://openalex.org/W6705026367","https://openalex.org/W6742162550","https://openalex.org/W6750448596"],"related_works":["https://openalex.org/W1983630549","https://openalex.org/W1976377428","https://openalex.org/W4254109928","https://openalex.org/W2150023094","https://openalex.org/W2963356946","https://openalex.org/W1996050943","https://openalex.org/W2034592155","https://openalex.org/W4200016955","https://openalex.org/W4236526691","https://openalex.org/W2003690377"],"abstract_inverted_index":{"NVIDIA's":[0,37],"software":[1],"does":[2],"not":[3],"offer":[4],"translation":[5],"of":[6,29,36,45,66],"assembly":[7],"code":[8],"to":[9],"binary":[10,51,98],"for":[11,42,68],"their":[12],"GPUs,":[13,38],"since":[14],"the":[15,31,56,81],"specifications":[16],"are":[17,78],"closed-source.":[18],"This":[19],"work":[20],"fills":[21],"that":[22,77],"gap.":[23],"We":[24],"develop":[25],"a":[26,64],"systematic":[27],"method":[28],"decoding":[30],"Instruction":[32],"Set":[33],"Architectures":[34],"(ISAs)":[35],"and":[39,53,70,75,89,102],"generating":[40],"assemblers":[41],"different":[43],"generations":[44],"GPUs.":[46],"Our":[47,84],"framework":[48],"enables":[49],"cross-architecture":[50],"analysis":[52],"transformation.":[54],"Making":[55],"ISA":[57],"accessible":[58],"in":[59,92],"this":[60],"manner":[61],"opens":[62],"up":[63],"world":[65],"opportunities":[67],"developers":[69],"researchers,":[71],"enabling":[72],"numerous":[73],"optimizations":[74],"explorations":[76],"unachievable":[79],"at":[80],"source-code":[82],"level.":[83],"infrastructure":[85],"has":[86],"already":[87],"benefited":[88],"been":[90],"adopted":[91],"important":[93],"applications":[94],"including":[95],"performance":[96],"tuning,":[97],"instrumentation,":[99],"resource":[100],"allocation,":[101],"memory":[103],"protection.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}