{"id":"https://openalex.org/W2963926583","doi":"https://doi.org/10.1109/padsw.2018.8645000","title":"GPGPU Performance Estimation with Core and Memory Frequency Scaling","display_name":"GPGPU Performance Estimation with Core and Memory Frequency Scaling","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2963926583","doi":"https://doi.org/10.1109/padsw.2018.8645000","mag":"2963926583"},"language":"en","primary_location":{"id":"doi:10.1109/padsw.2018.8645000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2018.8645000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5018867983","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0002-2986-967X"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730785","display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[{"id":"https://openalex.org/I4210159029","display_name":"Guangzhou HKUST Fok Ying Tung Research Institute","ror":"https://ror.org/05cvbj479","country_code":"CN","type":"facility","lineage":["https://openalex.org/I200769079","https://openalex.org/I4210159029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["Department of Computer Science, Hong Kong HKBU Institute of Research and Continuing Education, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong HKBU Institute of Research and Continuing Education, Shenzhen, China","institution_ids":["https://openalex.org/I4210159029"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018867983"],"corresponding_institution_ids":["https://openalex.org/I141568987"],"apc_list":null,"apc_paid":null,"fwci":5.8068,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96920068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"424"},"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":0.9991000294685364,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/frequency-scaling","display_name":"Frequency scaling","score":0.9067989587783813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8154215812683105},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7842104434967041},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6534649729728699},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6438387632369995},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5771984457969666},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5531908273696899},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.48902735114097595},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4737713634967804},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.42415037751197815},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.41881322860717773},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41576310992240906},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3609321713447571},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3515447676181793},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3460872769355774},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.11147701740264893}],"concepts":[{"id":"https://openalex.org/C157742956","wikidata":"https://www.wikidata.org/wiki/Q3237776","display_name":"Frequency scaling","level":3,"score":0.9067989587783813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8154215812683105},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7842104434967041},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6534649729728699},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6438387632369995},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5771984457969666},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5531908273696899},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.48902735114097595},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4737713634967804},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.42415037751197815},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41881322860717773},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41576310992240906},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3609321713447571},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3515447676181793},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3460872769355774},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.11147701740264893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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":2,"locations":[{"id":"doi:10.1109/padsw.2018.8645000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2018.8645000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-157721","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-157721","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W192356505","https://openalex.org/W753012316","https://openalex.org/W1555915743","https://openalex.org/W1904624772","https://openalex.org/W1978969737","https://openalex.org/W1979527452","https://openalex.org/W2033597569","https://openalex.org/W2038666141","https://openalex.org/W2074084090","https://openalex.org/W2080592089","https://openalex.org/W2086724906","https://openalex.org/W2092340922","https://openalex.org/W2093043622","https://openalex.org/W2099019585","https://openalex.org/W2110195531","https://openalex.org/W2142769604","https://openalex.org/W2155893237","https://openalex.org/W2163687928","https://openalex.org/W2167334577","https://openalex.org/W2170059648","https://openalex.org/W2233640613","https://openalex.org/W2522820499","https://openalex.org/W2529165666","https://openalex.org/W2725179571","https://openalex.org/W2762077810","https://openalex.org/W2794513473","https://openalex.org/W3005101099","https://openalex.org/W3152476980","https://openalex.org/W6622239757","https://openalex.org/W6673677911"],"related_works":["https://openalex.org/W2154351074","https://openalex.org/W2151223307","https://openalex.org/W2151046618","https://openalex.org/W1972148443","https://openalex.org/W1969233021","https://openalex.org/W2023400509","https://openalex.org/W2332054630","https://openalex.org/W2167646277","https://openalex.org/W2063573318","https://openalex.org/W2590100594"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"support":[4],"dynamic":[5],"voltage":[6],"and":[7,14,19,67,79,117],"frequency":[8,30,45,69],"scaling":[9],"to":[10,41,56,100,110,121],"balance":[11],"computational":[12],"performance":[13,21,119],"energy":[15,48],"consumption.":[16],"However,":[17],"simple":[18,108],"accurate":[20,89],"estimation":[22],"for":[23,35,47],"a":[24,52,72,112],"given":[25],"GPU":[26,62,84],"kernel":[27,118,127],"under":[28],"different":[29],"settings":[31],"is":[32,39],"still":[33],"lacking":[34],"real":[36,97],"hardware,":[37],"which":[38],"important":[40],"decide":[42],"the":[43,58,101],"best":[44],"configuration":[46],"saving.":[49],"We":[50],"reveal":[51],"fine-grained":[53],"analytical":[54],"model":[55,87,105],"estimate":[57],"execution":[59],"time":[60],"of":[61,76,114],"kernels":[63],"with":[64,96],"both":[65,77],"core":[66,78],"memory":[68,80],"scaling.":[70],"Over":[71],"2":[73],"x":[74],"range":[75],"frequencies":[81],"among":[82],"20":[83],"kernels,":[85],"our":[86,104],"achieves":[88],"results":[90],"(4.83":[91],"%":[92],"error":[93],"on":[94],"average)":[95],"hardware.":[98],"Compared":[99],"cycle-level":[102],"simulators,":[103],"only":[106],"needs":[107],"micro-benchmarks":[109],"extract":[111],"set":[113],"hardware":[115],"parameters":[116],"counters":[120],"produce":[122],"such":[123],"high":[124],"accuracy":[125],"without":[126],"source":[128],"analysis.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}