{"id":"https://openalex.org/W2052524559","doi":"https://doi.org/10.1145/2082156.2082168","title":"Domain-specific programmable design of scalable streaming-array for power-efficient stencil computation","display_name":"Domain-specific programmable design of scalable streaming-array for power-efficient stencil computation","publication_year":2011,"publication_date":"2011-12-19","ids":{"openalex":"https://openalex.org/W2052524559","doi":"https://doi.org/10.1145/2082156.2082168","mag":"2052524559"},"language":"en","primary_location":{"id":"doi:10.1145/2082156.2082168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2082156.2082168","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","raw_type":"journal-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/A5081752237","display_name":"Kentaro Sano","orcid":"https://orcid.org/0000-0002-6681-4192"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kentaro Sano","raw_affiliation_strings":["Sciences, Tohoku University","Sciences, Tohoku University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sciences, Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Sciences, Tohoku University#TAB#","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101413965","display_name":"Satoru Yamamoto","orcid":"https://orcid.org/0000-0003-1431-3035"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru Yamamoto","raw_affiliation_strings":["Sciences, Tohoku University","Sciences, Tohoku University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sciences, Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Sciences, Tohoku University#TAB#","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039865060","display_name":"Yoshiaki Hatsuda","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086981","display_name":"KOB (Germany)","ror":"https://ror.org/001ex3n55","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210086981"]},{"id":"https://openalex.org/I4210102023","display_name":"Koba Institute","ror":"https://ror.org/0166gt567","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102023"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Yoshiaki Hatsuda","raw_affiliation_strings":["Kobo, Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobo, Co., Ltd","institution_ids":["https://openalex.org/I4210102023","https://openalex.org/I4210086981"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081752237"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":0.5152,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66562327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"39","issue":"4","first_page":"44","last_page":"49"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8735509514808655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8066920638084412},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7669028043746948},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6221557855606079},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6032677888870239},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5701873898506165},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5394467115402222},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.48616334795951843},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.47638386487960815},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.46911221742630005},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46125754714012146},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36062514781951904},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.35077619552612305},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32628002762794495},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06793183088302612},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06259721517562866}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8735509514808655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066920638084412},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7669028043746948},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6221557855606079},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6032677888870239},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5701873898506165},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5394467115402222},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.48616334795951843},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.47638386487960815},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.46911221742630005},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46125754714012146},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36062514781951904},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.35077619552612305},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32628002762794495},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06793183088302612},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06259721517562866},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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:10.1145/2082156.2082168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2082156.2082168","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1590879322","https://openalex.org/W2002555321","https://openalex.org/W2096672917","https://openalex.org/W2101650420","https://openalex.org/W2111914791","https://openalex.org/W2132758316","https://openalex.org/W2139777359","https://openalex.org/W2150319905","https://openalex.org/W2154786353","https://openalex.org/W2612506596","https://openalex.org/W4300938688","https://openalex.org/W6635394987","https://openalex.org/W6776055689"],"related_works":["https://openalex.org/W1559264847","https://openalex.org/W2177020196","https://openalex.org/W2769005600","https://openalex.org/W1509422975","https://openalex.org/W1429949169","https://openalex.org/W2097757554","https://openalex.org/W2039378765","https://openalex.org/W2185562986","https://openalex.org/W4375947028","https://openalex.org/W3139770841"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,20,31,95,98,102,136],"domain-specific":[4],"programmable":[5,86,99,116],"design":[6,85,96,117],"of":[7,19,52,121,135],"custom":[8,72],"computing":[9,73],"machines":[10],"for":[11,79,106],"high-performance":[12],"stencil":[13],"computation.":[14],"Stencil":[15],"computation":[16],"is":[17,133],"one":[18],"typical":[21],"kernels":[22],"in":[23],"scientific":[24],"computations,":[25],"however":[26],"its":[27],"low":[28],"operational-intensity":[29],"makes":[30],"sustained":[32],"performance":[33],"limited":[34,89],"by":[35,60],"memory":[36],"bandwidth":[37],"on":[38],"recent":[39],"microprocessors":[40],"and":[41,74,81,101],"GPUs.":[42],"So":[43],"far":[44],"we":[45,84],"have":[46],"proposed":[47],"a":[48,64,119],"scalable":[49],"streaming-array":[50],"(SSA)":[51],"processing":[53],"elements,":[54],"which":[55,132],"provides":[56],"almost":[57],"linear":[58],"scalability":[59],"increasing":[61],"FPGAs":[62,112],"with":[63,88,110,118],"constant":[65],"externalmemory":[66],"bandwidth.":[67],"In":[68],"order":[69],"to":[70],"facilitate":[71],"efficiently":[75,128],"utilize":[76],"hardware":[77,125],"resources":[78,126],"various":[80],"complex":[82],"stencil-computations,":[83],"SSA":[87],"but":[90],"necessary":[91],"functionality.":[92],"We":[93],"show":[94],"concept,":[97],"structure":[100],"SIMD":[103],"instruction":[104],"set":[105],"SSA.":[107],"Prototype":[108],"implementation":[109],"nine":[111],"demonstrates":[113],"that":[114],"our":[115],"lot":[120],"floating-point":[122],"units":[123],"exploits":[124],"well,":[127],"achieving":[129],"260":[130],"GFlop/s,":[131],"87.4%":[134],"peak,":[137],"at":[138],"1295":[139],"MFlop/sW.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
