{"id":"https://openalex.org/W2799340985","doi":"https://doi.org/10.1145/3204919.3204920","title":"Performance-oriented Optimizations for OpenCL Streaming Kernels on the FPGA","display_name":"Performance-oriented Optimizations for OpenCL Streaming Kernels on the FPGA","publication_year":2018,"publication_date":"2018-05-02","ids":{"openalex":"https://openalex.org/W2799340985","doi":"https://doi.org/10.1145/3204919.3204920","mag":"2799340985"},"language":"en","primary_location":{"id":"doi:10.1145/3204919.3204920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3204919.3204920","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/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":["Argonne National Laboratory, Argonne, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["Argonne National Laboratory, Argonne, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":1.4252,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81829719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9995999932289124,"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":0.9962000250816345,"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":0.8915553689002991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.841189444065094},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6590653657913208},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.6014689803123474},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4936176538467407},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.48991984128952026},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4583825469017029},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.43830662965774536},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.39075666666030884}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8915553689002991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.841189444065094},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6590653657913208},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.6014689803123474},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4936176538467407},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.48991984128952026},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4583825469017029},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.43830662965774536},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39075666666030884},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3204919.3204920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3204919.3204920","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1653446932","https://openalex.org/W1969338303","https://openalex.org/W2000921084","https://openalex.org/W2021295531","https://openalex.org/W2033593649","https://openalex.org/W2088899870","https://openalex.org/W2114324808","https://openalex.org/W2133741166","https://openalex.org/W2159456929","https://openalex.org/W2271597743","https://openalex.org/W2333869848","https://openalex.org/W2365763746","https://openalex.org/W2475663704","https://openalex.org/W2523475814","https://openalex.org/W3011180447","https://openalex.org/W4206262605","https://openalex.org/W4234381228","https://openalex.org/W4241553019"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2355315220","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W2074043759","https://openalex.org/W2316202402","https://openalex.org/W2373535795","https://openalex.org/W2082487009","https://openalex.org/W3103262449","https://openalex.org/W3130402546"],"abstract_inverted_index":{"When":[0],"Field-programmable":[1],"gate":[2],"arrays":[3],"(FPGAs)":[4],"can":[5,39,98,124,142,179],"implement":[6],"streaming":[7,43,63,162],"applications":[8],"efficiently":[9],"and":[10,37,53,96,115],"high-level":[11],"synthesis":[12],"(HLS)":[13],"tools":[14],"allow":[15],"people,":[16],"who":[17],"have":[18],"little":[19],"hardware":[20],"design":[21],"knowledge,":[22],"to":[23,33,134,151,173,194],"evaluate":[24],"an":[25,80],"application":[26],"on":[27],"FPGAs,":[28],"there":[29],"is":[30],"a":[31,103,130,147,184,190],"need":[32],"understand":[34],"where":[35],"OpenCL":[36,68],"FPGA":[38,76,90],"play":[40],"in":[41],"the":[42,50,55,59,62,66,73,85,100,106,126,139,144,154,159,168,181],"domains.":[44],"To":[45,157],"this":[46],"end,":[47],"we":[48],"explore":[49],"implementation":[51],"space":[52],"discuss":[54],"techniques":[56,122,141],"of":[57,61,102,108,132,138,149,161,183,192],"optimizing":[58],"performance":[60,101,128,145,160,182],"kernels":[64,163],"using":[65],"Intel":[67],"SDK":[69],"for":[70],"FPGA.":[71],"On":[72],"Nallatech":[74],"385A":[75],"platform":[77],"that":[78,89,123],"features":[79],"Arria":[81],"10":[82],"GX1150":[83],"FPGA,":[84],"experimental":[86],"results":[87],"show":[88],"resources,":[91],"such":[92],"as":[93],"block":[94],"RAMs":[95],"DSPs,":[97],"limit":[99],"kernel":[104,127,186],"before":[105],"constraint":[107],"memory":[109],"bandwidth":[110],"takes":[111],"effect.":[112],"Kernel":[113],"vectorization":[114],"compute":[116,165],"unit":[117,166],"duplication":[118],"are":[119],"practical":[120],"optimization":[121],"improve":[125,143,158],"by":[129,146,189],"factor":[131,148,191],"2.8":[133],"10.":[135],"The":[136,176],"combination":[137],"two":[140],"3.3":[150],"16,":[152],"achieving":[153],"highest":[155],"performance.":[156],"with":[164],"duplication,":[167],"local":[169],"work":[170],"size":[171],"needs":[172],"be":[174],"tuned.":[175],"optimal":[177],"value":[178],"increase":[180],"duplicated":[185],"without":[187],"tuning":[188],"3":[193],"70.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"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"}