{"id":"https://openalex.org/W1989336131","doi":"https://doi.org/10.1145/1862648.1862651","title":"FPGA-Array with Bandwidth-Reduction Mechanism for Scalable and Power-Efficient Numerical Simulations Based on Finite Difference Methods","display_name":"FPGA-Array with Bandwidth-Reduction Mechanism for Scalable and Power-Efficient Numerical Simulations Based on Finite Difference Methods","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W1989336131","doi":"https://doi.org/10.1145/1862648.1862651","mag":"1989336131"},"language":"en","primary_location":{"id":"doi:10.1145/1862648.1862651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1862648.1862651","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","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":["Tohoku University","Tohoku Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Tohoku Univ.#TAB#","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085874089","display_name":"Luzhou Wang","orcid":null},"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":"Wang Luzhou","raw_affiliation_strings":["Tohoku University","Tohoku Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Tohoku Univ.#TAB#","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039865060","display_name":"Yoshiaki Hatsuda","orcid":null},"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":"Yoshiaki Hatsuda","raw_affiliation_strings":["Tohoku University","Tohoku Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Tohoku Univ.#TAB#","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106034741","display_name":"Takanori Iizuka","orcid":null},"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":"Takanori Iizuka","raw_affiliation_strings":["Tohoku University","Tohoku Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Tohoku Univ.#TAB#","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","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":["Tohoku University","Tohoku Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Tohoku Univ.#TAB#","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081752237"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":2.2757,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.88682228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":"4","first_page":"1","last_page":"35"},"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":0.9987000226974487,"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":0.9976999759674072,"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":0.8655807971954346},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7502521276473999},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.7132593989372253},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6816899180412292},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6529289484024048},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6171818971633911},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.5218861699104309},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4733298420906067},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4126850366592407},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39883100986480713},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2653999328613281},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17120757699012756},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09828728437423706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8655807971954346},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7502521276473999},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.7132593989372253},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6816899180412292},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6529289484024048},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6171818971633911},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.5218861699104309},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4733298420906067},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4126850366592407},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39883100986480713},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2653999328613281},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17120757699012756},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09828728437423706},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1862648.1862651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1862648.1862651","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2089300964","display_name":null,"funder_award_id":"2.07E+23","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1553214226","https://openalex.org/W1570895503","https://openalex.org/W1590879322","https://openalex.org/W1926163532","https://openalex.org/W1931987324","https://openalex.org/W1939837620","https://openalex.org/W1976535749","https://openalex.org/W1981252059","https://openalex.org/W1987243435","https://openalex.org/W1994266431","https://openalex.org/W2002335991","https://openalex.org/W2002555321","https://openalex.org/W2009895650","https://openalex.org/W2016421926","https://openalex.org/W2017369466","https://openalex.org/W2021748565","https://openalex.org/W2038785086","https://openalex.org/W2061624656","https://openalex.org/W2063261695","https://openalex.org/W2077897166","https://openalex.org/W2097586424","https://openalex.org/W2106521816","https://openalex.org/W2107076945","https://openalex.org/W2108308693","https://openalex.org/W2108784402","https://openalex.org/W2112980698","https://openalex.org/W2114393091","https://openalex.org/W2114702066","https://openalex.org/W2115002670","https://openalex.org/W2115294662","https://openalex.org/W2117638260","https://openalex.org/W2119697285","https://openalex.org/W2119722822","https://openalex.org/W2120527484","https://openalex.org/W2120820413","https://openalex.org/W2120978237","https://openalex.org/W2121430798","https://openalex.org/W2124408528","https://openalex.org/W2127466997","https://openalex.org/W2130048397","https://openalex.org/W2135593634","https://openalex.org/W2136268150","https://openalex.org/W2137272331","https://openalex.org/W2139774022","https://openalex.org/W2140549241","https://openalex.org/W2142063750","https://openalex.org/W2143011780","https://openalex.org/W2146717187","https://openalex.org/W2150405043","https://openalex.org/W2152567198","https://openalex.org/W2161112127","https://openalex.org/W2169039127","https://openalex.org/W2326999293","https://openalex.org/W2462300308","https://openalex.org/W2602816542","https://openalex.org/W2799261540","https://openalex.org/W4214544044","https://openalex.org/W4250395788","https://openalex.org/W4300761662","https://openalex.org/W6601341816"],"related_works":["https://openalex.org/W1509155667","https://openalex.org/W2518118925","https://openalex.org/W3208151864","https://openalex.org/W1564576805","https://openalex.org/W4254372399","https://openalex.org/W1967938402","https://openalex.org/W3145068070","https://openalex.org/W2386041993","https://openalex.org/W2917310154","https://openalex.org/W2150008128"],"abstract_inverted_index":{"For":[0],"scientific":[1,64],"numerical":[2],"simulation":[3],"that":[4,132,236,282,318],"requires":[5,295],"a":[6,50,76,84,124,137,146,309,341],"relatively":[7,332],"high":[8,92,253],"ratio":[9],"of":[10,17,33,86,106,110,142,154,169,179,190,208,228,243,255,267,301],"data":[11],"access":[12],"to":[13,23,37,57,88,118,128,245,263,270,291,298,339],"computation,":[14],"the":[15,21,34,72,102,119,129,151,166,173,177,184,206,225,237,240,264,271,283,304],"scalability":[16,109,262],"memory":[18,112],"bandwidth":[19,113,152,187,335],"is":[20,82,134,286],"key":[22],"performance":[24,116,200,227],"improvement,":[25],"and":[26,60,91,98,114,188,198,204,275,294,325],"therefore":[27,326],"custom-computing":[28],"machines":[29],"(CCMs)":[30],"are":[31],"one":[32],"promising":[35],"approaches":[36],"provide":[38,89],"bandwidth-aware":[39],"structures":[40],"tailored":[41],"for":[42,63,94,248,303,322],"individual":[43],"applications.":[44],"In":[45,277],"this":[46],"article,":[47],"we":[48,74,122,157,202,279,316],"propose":[49,158],"scalable":[51,342],"FPGA-array":[52],"with":[53,145,193,252,331],"bandwidth-reduction":[54],"mechanism":[55],"(BRM)":[56],"implement":[58,205],"high-performance":[59],"power-efficient":[61],"CCMs":[62],"simulations":[65],"based":[66,160],"on":[67,161],"finite":[68],"difference":[69],"methods.":[70],"With":[71,313],"FPGA-array,":[73],"construct":[75,340],"systolic":[77,103],"computational-memory":[78,104],"array":[79,120,141],"(SCMA),":[80],"which":[81],"given":[83],"minimum":[85],"programmability":[87],"flexibility":[90],"productivity":[93],"various":[95],"computing":[96,256],"kernels":[97],"boundary":[99],"computations.":[100],"Since":[101],"architecture":[105],"SCMA":[107,130,207,220,238,259,285],"provides":[108],"both":[111],"arithmetic":[115],"according":[117],"size,":[121],"introduce":[123],"homogeneously":[125],"partitioning":[126],"approach":[127],"so":[131],"it":[133,288],"extensible":[135],"over":[136,212],"1D":[138],"or":[139],"2D":[140],"FPGAs":[143,175,268,330],"connected":[144],"mesh":[147],"network.":[148],"To":[149,195],"satisfy":[150],"requirement":[153],"inter-FPGA":[155,191],"communication,":[156],"BRM":[159,164,319],"time-division":[162],"multiplexing.":[163],"decreases":[165],"required":[167],"number":[168,266],"communication":[170],"channels":[171],"between":[172,186],"adjacent":[174],"at":[176,222],"cost":[178],"delay":[180,189],"cycles.":[181],"We":[182,234],"formulate":[183],"trade-off":[185],"data-transfer":[192],"BRM.":[194],"demonstrate":[196,235,281],"feasibility":[197],"evaluate":[199],"quantitatively,":[201],"design":[203],"192":[209],"processing":[210],"elements":[211],"two":[213],"ALTERA":[214],"Stratix":[215],"II":[216],"FPGAs.":[217],"The":[218,258],"implemented":[219],"running":[221],"106MHz":[223],"has":[224,260],"peak":[226],"40.7":[229],"GFlops":[230,247],"in":[231],"single":[232],"precision.":[233],"achieves":[239],"sustained":[241],"performances":[242],"32.8":[244],"35.7":[246],"three":[249],"benchmark":[250,323],"computations":[251,306],"utilization":[254],"units.":[257],"complete":[261],"increasing":[265],"due":[269],"highly":[272],"localized":[273],"computation":[274],"communication.":[276],"addition,":[278],"also":[280],"FPGA-based":[284],"power-efficient:":[287],"consumes":[289],"69%":[290],"87%":[292],"power":[293],"only":[296],"2.8%":[297],"7.0%":[299],"energy":[300],"those":[302],"same":[305],"performed":[307],"by":[308],"3.4-GHz":[310],"Pentium4":[311],"processor.":[312],"software":[314],"simulation,":[315],"show":[317],"works":[320],"effectively":[321],"computations,":[324],"commercially":[327],"available":[328],"low-end":[329],"narrow":[333],"I/O":[334],"can":[336],"be":[337],"utilized":[338],"FPGA-array.":[343]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}