{"id":"https://openalex.org/W2134457957","doi":"https://doi.org/10.1109/fpt.2009.5377644","title":"Exploiting memory customization in FPGA for 3D stencil computations","display_name":"Exploiting memory customization in FPGA for 3D stencil computations","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2134457957","doi":"https://doi.org/10.1109/fpt.2009.5377644","mag":"2134457957"},"language":"en","primary_location":{"id":"doi:10.1109/fpt.2009.5377644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2009.5377644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Field-Programmable Technology","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100771200","display_name":"Muhammad Shafiq","orcid":"https://orcid.org/0000-0003-1909-9373"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Muhammad Shafiq","raw_affiliation_strings":["Computer Sciences, Barcelona Supercomputing Center, Barcelona, Spain","Departament dArquitectura de Computadors, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Sciences, Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"raw_affiliation_string":"Departament dArquitectura de Computadors, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074518408","display_name":"Miquel Peric\u00e0s","orcid":"https://orcid.org/0000-0002-7583-6609"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Miquel Pericas","raw_affiliation_strings":["Computer Sciences, Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Sciences, Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082199431","display_name":"R. de la Cruz","orcid":"https://orcid.org/0000-0002-2805-3417"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Raul de la Cruz","raw_affiliation_strings":["Computer Applications for Science and Engineering, Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Applications for Science and Engineering, Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027534318","display_name":"Mauricio Araya\u2013Polo","orcid":"https://orcid.org/0000-0002-5537-1840"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mauricio Araya-Polo","raw_affiliation_strings":["Computer Applications for Science and Engineering, Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Applications for Science and Engineering, Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113528111","display_name":"Nacho Navarro","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nacho Navarro","raw_affiliation_strings":["Departament dArquitectura de Computadors, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departament dArquitectura de Computadors, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075755125","display_name":"Eduard Ayguad\u00e9","orcid":"https://orcid.org/0000-0002-5146-103X"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eduard Ayguade","raw_affiliation_strings":["Computer Sciences, Barcelona Supercomputing Center, Barcelona, Spain","Departament dArquitectura de Computadors, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Sciences, Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"raw_affiliation_string":"Departament dArquitectura de Computadors, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"38","last_page":"45"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9988999962806702,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9983999729156494,"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/stencil","display_name":"Stencil","score":0.8021308779716492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7943570613861084},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6666616797447205},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5671365261077881},{"id":"https://openalex.org/keywords/virtex","display_name":"Virtex","score":0.54108726978302},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.5213759541511536},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4996917247772217},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.461870938539505},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.459987074136734},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.42325687408447266},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4152517318725586},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40360933542251587},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3416635990142822},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.31192976236343384},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.2496396005153656},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17245379090309143}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8021308779716492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943570613861084},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6666616797447205},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5671365261077881},{"id":"https://openalex.org/C2777674469","wikidata":"https://www.wikidata.org/wiki/Q20741011","display_name":"Virtex","level":3,"score":0.54108726978302},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5213759541511536},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4996917247772217},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.461870938539505},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.459987074136734},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.42325687408447266},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4152517318725586},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40360933542251587},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3416635990142822},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.31192976236343384},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2496396005153656},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17245379090309143},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpt.2009.5377644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2009.5377644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Field-Programmable Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1552060988","https://openalex.org/W1931987324","https://openalex.org/W1939837620","https://openalex.org/W2003741105","https://openalex.org/W2024454156","https://openalex.org/W2035947216","https://openalex.org/W2052839611","https://openalex.org/W2055253125","https://openalex.org/W2076535184","https://openalex.org/W2108784402","https://openalex.org/W2119042753","https://openalex.org/W2119609467","https://openalex.org/W2130657589","https://openalex.org/W2151664616","https://openalex.org/W2154786353","https://openalex.org/W2159535674","https://openalex.org/W3152199537","https://openalex.org/W4234392772","https://openalex.org/W4249968602","https://openalex.org/W6640307903","https://openalex.org/W6659459173"],"related_works":["https://openalex.org/W2769005600","https://openalex.org/W2097757554","https://openalex.org/W2039378765","https://openalex.org/W2185562986","https://openalex.org/W4401408752","https://openalex.org/W2887888236","https://openalex.org/W2056599241","https://openalex.org/W2912790413","https://openalex.org/W3091819417","https://openalex.org/W4287645235"],"abstract_inverted_index":{"3D":[0,57,200],"stencil":[1,131,201],"computations":[2],"are":[3],"compute-intensive":[4],"kernels":[5,21],"often":[6],"appearing":[7],"in":[8,18,104,111,116],"high-performance":[9],"scientific":[10],"and":[11,89,108,137,145,152],"engineering":[12],"applications.":[13],"The":[14,49,77,141,164],"key":[15],"to":[16,129,147,153],"efficiency":[17],"these":[19],"memory-bound":[20],"is":[22,82,143],"full":[23],"exploitation":[24],"of":[25,41,56,79,101,134,181],"data":[26,44,132,196],"reuse.":[27],"This":[28,127],"paper":[29],"explores":[30],"the":[31,39,53,60,80,95,105,112,154,160,174,178,182],"design":[32,55,86,114],"aspects":[33],"for":[34],"3D-Stencil":[35],"implementations":[36],"that":[37],"maximize":[38],"reuse":[40],"all":[42],"input":[43],"on":[45,52,122,159],"a":[46,98,117,123,130,189],"FPGA":[47,165,175],"architecture.":[48],"work":[50],"focuses":[51],"architectural":[54],"stencils":[58],"with":[59],"form":[61],"n":[62,70,92],"\u00d7":[63,67],"(n":[64],"+":[65],"1)":[66],"n,":[68],"where":[69],"=":[71,93],"{2,":[72],"4,":[73],"6,":[74],"8,":[75,94],"...}.":[76],"performance":[78],"architecture":[81],"evaluated":[83],"using":[84],"two":[85,148],"approaches,":[87],"\u00bfMulti-Volume\u00bf":[88,113],"\u00bfSingle-Volume\u00bf.":[90],"When":[91],"designs":[96],"achieve":[97,169],"sustained":[99],"throughput":[100,197],"55.5":[102],"GFLOPS":[103,110],"\u00bfSingle-Volume\u00bf":[106],"approach":[107,115],"103":[109],"100-200":[118],"MHz":[119],"multi-rate":[120],"implementation":[121,142],"Virtex-4":[124],"LX200":[125],"FPGA.":[126],"corresponds":[128],"delivery":[133],"1500":[135],"bytes/cycle":[136,139],"2800":[138],"respectively.":[140],"analyzed":[144],"compared":[146],"CPU":[149],"cache":[150],"approaches":[151,166],"statically":[155],"scheduled":[156],"local":[157],"stores":[158],"IBM":[161],"PowerXCell":[162],"8i.":[163],"designed":[167],"here":[168],"much":[170],"higher":[171],"bandwidth":[172],"despite":[173],"device":[176],"being":[177],"least":[179],"recent":[180],"chips":[183],"considered.":[184],"These":[185],"numbers":[186],"show":[187],"how":[188],"custom":[190],"memory":[191],"organization":[192],"can":[193],"provide":[194],"large":[195],"when":[198],"implementing":[199],"kernels.":[202]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
