{"id":"https://openalex.org/W2793885849","doi":"https://doi.org/10.1145/3174243.3174967","title":"Evaluation of OpenCL Performance-oriented Optimizations for Streaming Kernels on the FPGA","display_name":"Evaluation of OpenCL Performance-oriented Optimizations for Streaming Kernels on the FPGA","publication_year":2018,"publication_date":"2018-02-15","ids":{"openalex":"https://openalex.org/W2793885849","doi":"https://doi.org/10.1145/3174243.3174967","mag":"2793885849"},"language":"en","primary_location":{"id":"doi:10.1145/3174243.3174967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3174243.3174967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","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":true,"raw_author_name":"Zheming Jin","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA"],"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"],"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":["https://openalex.org/A5101790023"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":0.2525,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46418968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"287"},"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/T11181","display_name":"Advanced Data Storage Technologies","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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.863125741481781},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8409864902496338},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6324637532234192},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.55443274974823},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47145041823387146},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.42985332012176514},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3982261121273041},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15746301412582397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.863125741481781},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8409864902496338},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6324637532234192},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.55443274974823},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47145041823387146},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.42985332012176514},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3982261121273041},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15746301412582397},{"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},{"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:10.1145/3174243.3174967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3174243.3174967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2082487009","https://openalex.org/W2373535795","https://openalex.org/W3103262449","https://openalex.org/W3130402546"],"abstract_inverted_index":{"The":[0,102,125,177],"streaming":[1,39,79,130],"applications":[2],"efficiently":[3],"and":[4,26,33,71,99,113,139,156,204],"High-level":[5],"synthesis":[6],"(HLS)":[7],"tools":[8],"allow":[9],"people":[10],"without":[11],"complex":[12],"hardware":[13],"design":[14],"knowledge":[15],"to":[16,29,175,201,217,220],"evaluate":[17,45],"an":[18,24,60],"application":[19],"on":[20,52],"FPGAs,":[21],"there":[22],"is":[23,110,121],"opportunity":[25],"a":[27,118,171,213],"need":[28],"understand":[30],"where":[31],"OpenCL":[32,50],"FPGA":[34,56,97,133],"can":[35,141,165,183,208],"play":[36],"in":[37],"the":[38,46,49,53,68,73,78,82,87,90,96,105,114,129,143,147,167,180,185,190,196,205,210,221],"domains.":[40],"To":[41,188],"this":[42],"end,":[43],"we":[44,66],"overhead":[47,92],"of":[48,95,104,117,128,149,173,179,192,215],"infrastructure":[51,91],"Nallatech":[54],"385A":[55],"board":[57],"that":[58,164],"features":[59],"Arria":[61],"10":[62],"GX1150":[63],"FPGA.":[64],"Then":[65],"explore":[67],"implementation":[69,120],"space":[70],"discuss":[72],"performance":[74,145,169,191,211],"optimization":[75,162],"techniques":[76,163,182],"for":[77],"kernels":[80,131],"using":[81],"OpenCL-to-FPGA":[83],"HLS":[84],"tool.":[85],"On":[86],"target":[88],"platform,":[89],"requires":[93],"12%":[94],"memory":[98,150],"logic":[100],"resources.":[101],"latency":[103],"single":[106],"work-item":[107],"kernel":[108,119,144,168],"execution":[109],"11":[111],"us":[112],"maximum":[115],"frequency":[116],"around":[122],"300":[123],"MHz.":[124],"experimental":[126],"results":[127],"show":[132],"resources,":[134],"such":[135],"as":[136],"block":[137],"RAMs":[138],"DSPs,":[140],"limit":[142],"before":[146],"constraint":[148],"bandwidth":[151],"takes":[152],"effect.":[153],"Kernel":[154],"vectorization":[155],"compute":[157,193],"unit":[158,194],"duplication":[159],"are":[160],"practical":[161],"improve":[166,189],"by":[170,212],"factor":[172,214],"2":[174],"10.":[176],"combination":[178],"two":[181],"achieve":[184],"best":[186],"performance.":[187],"duplication,":[195],"local":[197],"work":[198],"size":[199],"needs":[200],"be":[202],"tuned":[203],"optimal":[206],"value":[207],"increase":[209],"3":[216],"70":[218],"compared":[219],"default":[222],"value.":[223]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}