{"id":"https://openalex.org/W3157304207","doi":"https://doi.org/10.1109/iscas51556.2021.9401255","title":"Dynamic Optimizations in GPU Using Roofline Model","display_name":"Dynamic Optimizations in GPU Using Roofline Model","publication_year":2021,"publication_date":"2021-04-27","ids":{"openalex":"https://openalex.org/W3157304207","doi":"https://doi.org/10.1109/iscas51556.2021.9401255","mag":"3157304207"},"language":"en","primary_location":{"id":"doi:10.1109/iscas51556.2021.9401255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5011782290","display_name":"Winnie Thomas","orcid":"https://orcid.org/0000-0001-8341-2403"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Winnie Thomas","raw_affiliation_strings":["Computer Architecture and Dependable Systems Laboratory Dept. of Electrical Engineering, Indian Institute of Technology Bombay, India"],"affiliations":[{"raw_affiliation_string":"Computer Architecture and Dependable Systems Laboratory Dept. of Electrical Engineering, Indian Institute of Technology Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019947309","display_name":"Suryakant Toraskar","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suryakant Toraskar","raw_affiliation_strings":["Computer Architecture and Dependable Systems Laboratory Dept. of Electrical Engineering, Indian Institute of Technology Bombay, India"],"affiliations":[{"raw_affiliation_string":"Computer Architecture and Dependable Systems Laboratory Dept. of Electrical Engineering, Indian Institute of Technology Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073587430","display_name":"Virendra Singh","orcid":"https://orcid.org/0000-0002-7035-7844"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Virendra Singh","raw_affiliation_strings":["Computer Architecture and Dependable Systems Laboratory Dept. of Electrical Engineering, Indian Institute of Technology Bombay, India"],"affiliations":[{"raw_affiliation_string":"Computer Architecture and Dependable Systems Laboratory Dept. of Electrical Engineering, Indian Institute of Technology Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011782290"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":1.8423,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84443042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9984999895095825,"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/bottleneck","display_name":"Bottleneck","score":0.8712519407272339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8569107055664062},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6271215677261353},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5963674783706665},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5907201766967773},{"id":"https://openalex.org/keywords/human-multitasking","display_name":"Human multitasking","score":0.5537638068199158},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5209035277366638},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.49440503120422363},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.45550206303596497},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.453813761472702},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4179793894290924},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4158819615840912},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.29521244764328003},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.15795236825942993},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1386098861694336}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8712519407272339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8569107055664062},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6271215677261353},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5963674783706665},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5907201766967773},{"id":"https://openalex.org/C107418235","wikidata":"https://www.wikidata.org/wiki/Q1520565","display_name":"Human multitasking","level":2,"score":0.5537638068199158},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5209035277366638},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.49440503120422363},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.45550206303596497},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.453813761472702},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4179793894290924},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4158819615840912},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29521244764328003},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.15795236825942993},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1386098861694336},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"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:10.1109/iscas51556.2021.9401255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1973573211","https://openalex.org/W1979527452","https://openalex.org/W1984993578","https://openalex.org/W2002555321","https://openalex.org/W2024122052","https://openalex.org/W2037518952","https://openalex.org/W2055844022","https://openalex.org/W2063750261","https://openalex.org/W2080592089","https://openalex.org/W2131274487","https://openalex.org/W2134953833","https://openalex.org/W2150851481","https://openalex.org/W2152517358","https://openalex.org/W2323693848","https://openalex.org/W2510980549","https://openalex.org/W2607112060","https://openalex.org/W2795326697","https://openalex.org/W2883073617","https://openalex.org/W2891285910","https://openalex.org/W2900580414","https://openalex.org/W4243035950"],"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/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Massively":[0],"parallel":[1],"processors":[2],"such":[3],"as":[4],"graphics":[5],"processing":[6],"units":[7],"(GPUs)":[8],"often":[9],"face":[10],"the":[11,53,78,82,88,100],"challenge":[12],"of":[13,21,56,87],"resource":[14,19,94],"underutilization":[15],"due":[16],"to":[17,36,67,108],"varying":[18],"proclivity":[20],"workloads.":[22],"Running":[23],"multiple":[24],"applications":[25,62,91],"on":[26,52,64,104],"a":[27,42,111],"GPU":[28,89],"has":[29],"been":[30],"an":[31],"efficient":[32],"and":[33,84,106],"known":[34],"alternative":[35],"mitigate":[37],"underutilization.":[38],"This":[39],"paper":[40],"proposes":[41],"multi-application":[43],"oriented":[44],"framework":[45,60],"that":[46,77],"carries":[47],"out":[48],"dynamic":[49,97],"optimizations":[50,80,98],"based":[51,63],"operational":[54,65],"intensities":[55,66],"various":[57],"applications.":[58],"Our":[59],"analyzes":[61],"identify":[68],"their":[69],"bottleneck":[70],"resources":[71],"using":[72],"Roofline":[73],"model.":[74],"We":[75],"demonstrate":[76],"proposed":[79],"improve":[81,99],"utilization":[83],"system-wide":[85],"throughput":[86],"co-running":[90],"with":[92],"irregular":[93],"demands.":[95],"The":[96],"performance":[101],"by":[102],"14.8%":[103],"average":[105],"up":[107],"72.4%":[109],"over":[110],"state-of-the-art":[112],"spatial":[113],"multitasking":[114],"technique.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}