{"id":"https://openalex.org/W2920346706","doi":"https://doi.org/10.1109/tencon.2018.8650390","title":"Runtime Profiling of OpenCL Workloads Using LLVM-based Code Instrumentation","display_name":"Runtime Profiling of OpenCL Workloads Using LLVM-based Code Instrumentation","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2920346706","doi":"https://doi.org/10.1109/tencon.2018.8650390","mag":"2920346706"},"language":"en","primary_location":{"id":"doi:10.1109/tencon.2018.8650390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2018.8650390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2018 - 2018 IEEE Region 10 Conference","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/A5085503041","display_name":"Yongseung Yu","orcid":"https://orcid.org/0000-0001-9838-4310"},"institutions":[{"id":"https://openalex.org/I94588446","display_name":"Hongik University","ror":"https://ror.org/00egdv862","country_code":"KR","type":"education","lineage":["https://openalex.org/I94588446"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongseung Yu","raw_affiliation_strings":["Hongik University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hongik University, Seoul, Korea","institution_ids":["https://openalex.org/I94588446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019899003","display_name":"Seokwon Kang","orcid":"https://orcid.org/0000-0003-0017-592X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokwon Kang","raw_affiliation_strings":["Hanyang University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086980677","display_name":"Yongjun Park","orcid":"https://orcid.org/0000-0003-3725-0380"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongjun Park","raw_affiliation_strings":["Hanyang University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1520","last_page":"1524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9922000169754028,"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":0.9110648036003113},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.7969045639038086},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7910425662994385},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.623985230922699},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5818278193473816},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5087864995002747},{"id":"https://openalex.org/keywords/intermediate-language","display_name":"Intermediate language","score":0.49788641929626465},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.46893027424812317},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.42738014459609985},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.411428838968277},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3826060891151428},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3436880111694336},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1397036910057068}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9110648036003113},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7969045639038086},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7910425662994385},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.623985230922699},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5818278193473816},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5087864995002747},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.49788641929626465},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.46893027424812317},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.42738014459609985},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.411428838968277},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3826060891151428},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3436880111694336},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1397036910057068}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon.2018.8650390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2018.8650390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2018 - 2018 IEEE Region 10 Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2128120785"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2546223573","https://openalex.org/W2370314112","https://openalex.org/W1912958759"],"abstract_inverted_index":{"GPUs,":[0],"which":[1,60],"are":[2],"widely":[3],"used":[4],"high-performance":[5],"hardware":[6],"accelerators":[7],"in":[8,45],"heterogeneous":[9],"computing,":[10],"and":[11,19],"programming":[12,47],"models":[13],"for":[14,68],"architectures":[15],"such":[16],"as":[17],"OpenCL":[18,70],"CUDA,":[20],"have":[21],"recently":[22],"been":[23],"developed":[24],"to":[25],"achieve":[26],"high":[27],"productivity.":[28],"LLVM":[29,40],"is":[30],"an":[31],"open-source":[32],"compiler":[33],"infrastructure":[34],"that":[35],"enables":[36],"low-level":[37],"optimization":[38],"through":[39,64],"intermediate":[41],"representation":[42],"(LLVM":[43],"IR)":[44],"various":[46],"language":[48],"environments.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"a":[55],"fully-automatic":[56],"Dynamic":[57],"Profiling":[58],"framework":[59],"performs":[61],"instruction-level":[62],"analysis":[63],"IR-level":[65],"code":[66],"instrumentation":[67],"typical":[69],"workload":[71],"kernels.":[72]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}