{"id":"https://openalex.org/W2886841777","doi":"https://doi.org/10.1109/ipdpsw.2018.00115","title":"Power and Performance Tradeoff of a Floating-Point Intensive Kernel on OpenCL FPGA Platform","display_name":"Power and Performance Tradeoff of a Floating-Point Intensive Kernel on OpenCL FPGA Platform","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2886841777","doi":"https://doi.org/10.1109/ipdpsw.2018.00115","mag":"2886841777"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2018.00115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2018.00115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","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/A5101790023","display_name":"Zheming Jin","orcid":"https://orcid.org/0000-0002-7197-780X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheming Jin","raw_affiliation_strings":["Leadership Computing Facility, Argonne National Laboratory, Argonne, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leadership Computing Facility, Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050512119","display_name":"Hal Finkel","orcid":"https://orcid.org/0000-0002-7551-7122"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hal Finkel","raw_affiliation_strings":["Leadership Computing Facility, Argonne National Laboratory, Argonne, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leadership Computing Facility, Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1877,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79591601,"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":"716","last_page":"720"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.996999979019165,"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":0.9969000220298767,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8320484161376953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7754706144332886},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7688903212547302},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6270133852958679},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5135212540626526},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4756440818309784},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.4633074402809143},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.41704148054122925},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2792799472808838}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8320484161376953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754706144332886},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7688903212547302},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6270133852958679},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5135212540626526},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4756440818309784},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.4633074402809143},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.41704148054122925},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2792799472808838},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw.2018.00115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2018.00115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W324279178","https://openalex.org/W2000921084","https://openalex.org/W2026418498","https://openalex.org/W2043957526","https://openalex.org/W2065409092","https://openalex.org/W2096280516","https://openalex.org/W2105011467","https://openalex.org/W2115002670","https://openalex.org/W2122078011","https://openalex.org/W2343695530","https://openalex.org/W2345615132","https://openalex.org/W2472500612","https://openalex.org/W2475663704","https://openalex.org/W2480421838","https://openalex.org/W2746871167","https://openalex.org/W2786263629","https://openalex.org/W4206262605","https://openalex.org/W4252821989","https://openalex.org/W6748392146"],"related_works":["https://openalex.org/W2085105049","https://openalex.org/W2370279919","https://openalex.org/W2152301037","https://openalex.org/W3028347934","https://openalex.org/W3203561460","https://openalex.org/W2094210932","https://openalex.org/W1836109266","https://openalex.org/W4251138667","https://openalex.org/W2384717171","https://openalex.org/W2185692674"],"abstract_inverted_index":{"As":[0],"power":[1,14,64,83],"is":[2,29,139,157],"recognized":[3],"as":[4],"one":[5],"of":[6,47,50,85,101,132],"first-order":[7],"constraints":[8],"in":[9],"high-performance":[10,37],"computing,":[11],"understanding":[12],"how":[13],"and":[15,38,63,82,98,118,145],"performance":[16,62,81,97,129],"are":[17],"affected":[18],"using":[19,65],"a":[20,25,33,51,56],"high-level":[21,71],"synthesis":[22,72],"tool":[23,73],"for":[24,36,74],"floating-point":[26,52],"intensive":[27,53],"kernel":[28,54,87,103,134],"important.":[30],"FPGAs":[31],"offer":[32],"promising":[34],"solution":[35],"energyefficient":[39],"computing":[40],"applications.":[41],"This":[42],"paper":[43],"presents":[44],"the":[45,48,61,78,86,96,102,128,133,137,143,149,155],"impact":[46],"optimizations":[49],"from":[55],"geographical":[57],"information":[58],"system":[59],"upon":[60],"an":[66,69,90,106,111,119],"FPGA.":[67],"Using":[68],"OpenCL-based":[70],"FPGAs,":[75],"we":[76],"evaluate":[77],"resource":[79],"usage,":[80],"consumption":[84],"implementations":[88,104],"on":[89,105,136,154],"Arria10-based":[91],"FPGA":[92,138,156],"platform.":[93],"We":[94],"compare":[95],"energy":[99],"efficiency":[100],"Arria":[107],"10":[108],"GX1150":[109],"FPGA,":[110],"Intel's":[112],"Xeon":[113],"Phi":[114],"Knights":[115],"Landing":[116],"CPU,":[117],"NVIDIA's":[120],"Tesla":[121],"K80":[122],"GPU.":[123,150],"Our":[124],"experiment":[125],"shows":[126],"that":[127],"per":[130],"watt":[131],"implementation":[135],"1.79X":[140],"better":[141,147],"than":[142,148],"CPU":[144],"1.56X":[146],"The":[151],"execution":[152],"time":[153],"approximately":[158],"2.9X":[159],"slower.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}