{"id":"https://openalex.org/W2954398131","doi":"https://doi.org/10.1145/3318170.3318182","title":"Profiling OpenCL Kernels Using Wavefront Occupancy with Radeon GPU Profiler","display_name":"Profiling OpenCL Kernels Using Wavefront Occupancy with Radeon GPU Profiler","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2954398131","doi":"https://doi.org/10.1145/3318170.3318182","mag":"2954398131"},"language":"en","primary_location":{"id":"doi:10.1145/3318170.3318182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318170.3318182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on OpenCL","raw_type":"proceedings-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/A5038365055","display_name":"Perhaad Mistry","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Perhaad Mistry","raw_affiliation_strings":["Advanced Micro Devices, Inc, Boxborough, Massachusetts"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc, Boxborough, Massachusetts","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108523265","display_name":"Budirijanto Purnomo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Budirijanto Purnomo","raw_affiliation_strings":["Advanced Micro Devices, Inc, Boxborough, Massachusetts"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc, Boxborough, Massachusetts","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210137977"],"apc_list":null,"apc_paid":null,"fwci":0.4935,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6091692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9901999831199646,"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":0.9901999831199646,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9855999946594238,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9829000234603882,"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":0.7749664783477783},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.7003999352455139},{"id":"https://openalex.org/keywords/occupancy","display_name":"Occupancy","score":0.6055730581283569},{"id":"https://openalex.org/keywords/wavefront","display_name":"Wavefront","score":0.5048266053199768},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4695095717906952},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43898364901542664},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4182334542274475},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3221464157104492},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20050156116485596},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11910691857337952},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.10571590065956116},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.08319962024688721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749664783477783},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7003999352455139},{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.6055730581283569},{"id":"https://openalex.org/C165699331","wikidata":"https://www.wikidata.org/wiki/Q461533","display_name":"Wavefront","level":2,"score":0.5048266053199768},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4695095717906952},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43898364901542664},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4182334542274475},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3221464157104492},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20050156116485596},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11910691857337952},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.10571590065956116},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.08319962024688721},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3318170.3318182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318170.3318182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on OpenCL","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W780656674","https://openalex.org/W2563180316"],"related_works":["https://openalex.org/W4282043467","https://openalex.org/W2105697914","https://openalex.org/W3093197249","https://openalex.org/W1968324288","https://openalex.org/W1540010871","https://openalex.org/W1656096860","https://openalex.org/W2095928260","https://openalex.org/W2268149564","https://openalex.org/W1984739956","https://openalex.org/W2763312740"],"abstract_inverted_index":{"Profiling":[0],"OpenCL":[1,99,112],"[3]":[2],"applications":[3],"on":[4],"modern":[5],"GPUs":[6],"is":[7,92],"usually":[8],"limited":[9],"to":[10,42,103],"gathering":[11,18],"timestamps":[12],"from":[13],"the":[14,33,72,85,101,105],"host":[15],"side":[16],"or":[17,71],"performance":[19,37,47,94],"counter":[20],"data":[21],"for":[22],"a":[23,57,75,93],"complete":[24],"GPU":[25,76,87],"kernel.":[26],"In":[27,80],"this":[28,81],"presentation,":[29],"we":[30,83],"will":[31],"show":[32],"limitations":[34],"of":[35,50,74,107],"existing":[36],"counter-based":[38,48],"methods":[39,49],"with":[40],"respect":[41],"optimizing":[43],"complex":[44],"applications.":[45],"Existing":[46],"profiling":[51],"only":[52],"provide":[53,63],"information":[54],"aggregated":[55],"over":[56,78],"kernel's":[58,113],"lifetime":[59],"and":[60],"does":[61],"not":[62],"insight":[64],"into":[65],"load":[66],"balancing":[67],"across":[68],"shader":[69],"engines":[70],"behavior":[73],"kernel":[77],"time.":[79],"paper,":[82],"present":[84],"Radeon":[86],"Profiler":[88],"(RGP)":[89],"[2].":[90],"RGP":[91],"analysis":[95],"tool":[96],"that":[97],"enables":[98],"developers":[100],"ability":[102],"understand":[104],"utilization":[106],"their":[108,111],"device":[109],"during":[110],"execution.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
