{"id":"https://openalex.org/W2523475814","doi":"https://doi.org/10.1109/iccd.2016.7753287","title":"Tuning Stencil codes in OpenCL for FPGAs","display_name":"Tuning Stencil codes in OpenCL for FPGAs","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2523475814","doi":"https://doi.org/10.1109/iccd.2016.7753287","mag":"2523475814"},"language":"en","primary_location":{"id":"doi:10.1109/iccd.2016.7753287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2016.7753287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 34th International Conference on Computer Design (ICCD)","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/A5044515234","display_name":"Qi Jia","orcid":"https://orcid.org/0000-0003-3466-4000"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qi Jia","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, North Carolina State University, Raleigh, North Carolina"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, North Carolina State University, Raleigh, North Carolina","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072755725","display_name":"Huiyang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyang Zhou","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, North Carolina State University, Raleigh, North Carolina"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, North Carolina State University, Raleigh, North Carolina","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044515234"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":6.3995,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.97141817,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"4","issue":null,"first_page":"249","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9943000078201294,"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":0.9934999942779541,"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/computer-science","display_name":"Computer science","score":0.886105477809906},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7739955186843872},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7034302949905396},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6321592926979065},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6287351846694946},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5341210961341858},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42865002155303955},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2829608619213104},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.2314324975013733},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06998255848884583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.886105477809906},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7739955186843872},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7034302949905396},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6321592926979065},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6287351846694946},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5341210961341858},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42865002155303955},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2829608619213104},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2314324975013733},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06998255848884583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccd.2016.7753287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2016.7753287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 34th International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.lib.ncsu.edu:1840.20/22928","is_oa":false,"landing_page_url":"http://www.lib.ncsu.edu/resolver/1840.20/22928","pdf_url":null,"source":{"id":"https://openalex.org/S4306402468","display_name":"NCSU Libraries Repository (North Carolina State University Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I137902535","host_organization_name":"North Carolina State University","host_organization_lineage":["https://openalex.org/I137902535"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2006682606","https://openalex.org/W2063186542","https://openalex.org/W2120335261","https://openalex.org/W2122862680","https://openalex.org/W2134457957","https://openalex.org/W2144004530","https://openalex.org/W2154078685","https://openalex.org/W2154786353","https://openalex.org/W2171318387","https://openalex.org/W2183420951","https://openalex.org/W2317369144","https://openalex.org/W2335592298","https://openalex.org/W3152199537"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2008005532","https://openalex.org/W1971603802","https://openalex.org/W1977185554","https://openalex.org/W2076165488","https://openalex.org/W1618681060"],"abstract_inverted_index":{"OpenCL":[0,19,42,47,62,81],"is":[1,34,43,55],"designed":[2],"as":[3],"a":[4,27],"parallel":[5],"programming":[6,29],"framework":[7],"to":[8,49,74,117,130],"support":[9],"heterogeneous":[10],"computing":[11],"platforms.":[12],"The":[13],"implicit":[14],"or":[15],"explicit":[16],"parallelism":[17],"in":[18,96],"kernel":[20],"code":[21,82,162],"enables":[22],"efficient":[23],"FPGA":[24,32,157],"implementation":[25],"from":[26,37],"high-level":[28],"abstraction.":[30],"However,":[31],"architecture":[33],"completely":[35],"different":[36,168],"GPU":[38],"architecture,":[39],"for":[40,67,84,93,142],"which":[41],"widely":[44],"used.":[45],"Tuning":[46],"codes":[48],"achieve":[50,115,137],"high":[51],"performance":[52,122,166],"on":[53,87,172],"FPGAs":[54],"an":[56],"open":[57],"problem":[58],"and":[59,64,100,109,139,145],"the":[60,98,125,143,156,165],"existing":[61],"tools":[63],"optimizations":[65,83],"proposed":[66],"CPUs/GPUs":[68],"may":[69],"not":[70],"be":[71],"directly":[72],"applicable":[73],"FPGAs.":[75,88,173],"In":[76],"this":[77],"paper,":[78],"we":[79],"explore":[80],"stencil":[85,94],"computations":[86],"We":[89],"propose":[90],"tuning":[91],"processes":[92],"kernels":[95,113,136],"both":[97],"Single-Task":[99],"NDRange":[101],"modes.":[102],"Our":[103],"optimized":[104,135],"1D":[105],"convolution,":[106],"2D":[107,110],"convolution":[108],"Jacobi":[111],"iteration":[112],"can":[114],"up":[116],"two":[118],"orders":[119],"of":[120,155,167,170],"magnitude":[121],"improvement":[123],"over":[124],"na\u00efve":[126],"kernels.":[127],"Also,":[128],"compared":[129],"Altera":[131],"design":[132],"examples":[133],"our":[134],"7.1\u00d7":[138],"3.5\u00d7":[140],"speedups":[141],"Sobel":[144],"Time-Domain":[146],"FIR":[147],"Filter,":[148],"respectively.":[149],"This":[150],"study":[151],"also":[152],"includes":[153],"benchmarking":[154],"memory":[158,171],"system,":[159],"revealing":[160],"how":[161],"patterns":[163],"affect":[164],"types":[169]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
