{"id":"https://openalex.org/W2604282092","doi":"https://doi.org/10.1109/tpds.2017.2691770","title":"FPGA-Based Scalable and Power-Efficient Fluid Simulation using Floating-Point DSP Blocks","display_name":"FPGA-Based Scalable and Power-Efficient Fluid Simulation using Floating-Point DSP Blocks","publication_year":2017,"publication_date":"2017-04-06","ids":{"openalex":"https://openalex.org/W2604282092","doi":"https://doi.org/10.1109/tpds.2017.2691770","mag":"2604282092"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2017.2691770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2691770","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed 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":["Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","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":["Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081752237"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":5.3269,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.96854476,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"28","issue":"10","first_page":"2823","last_page":"2837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9970999956130981,"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":0.9937000274658203,"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":0.8505916595458984},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7537926435470581},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7163486480712891},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6893466711044312},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.6192135810852051},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6060258150100708},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5084053874015808},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.48539718985557556},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4562910199165344},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.45537859201431274},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45382368564605713},{"id":"https://openalex.org/keywords/reconfigurable-computing","display_name":"Reconfigurable computing","score":0.44445478916168213},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.41869550943374634},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3525112271308899},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.34532153606414795},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08078044652938843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8505916595458984},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7537926435470581},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7163486480712891},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6893466711044312},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.6192135810852051},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6060258150100708},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5084053874015808},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.48539718985557556},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4562910199165344},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.45537859201431274},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45382368564605713},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.44445478916168213},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.41869550943374634},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3525112271308899},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.34532153606414795},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08078044652938843},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2017.2691770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2691770","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"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":47,"referenced_works":["https://openalex.org/W594283781","https://openalex.org/W1757537413","https://openalex.org/W1973455510","https://openalex.org/W1976346389","https://openalex.org/W1976535749","https://openalex.org/W1981252059","https://openalex.org/W1989336131","https://openalex.org/W1990604500","https://openalex.org/W1996725964","https://openalex.org/W2002555321","https://openalex.org/W2025347051","https://openalex.org/W2026659976","https://openalex.org/W2053304483","https://openalex.org/W2061488635","https://openalex.org/W2061624656","https://openalex.org/W2062364940","https://openalex.org/W2064744742","https://openalex.org/W2066804546","https://openalex.org/W2066886134","https://openalex.org/W2076361081","https://openalex.org/W2087497493","https://openalex.org/W2091596155","https://openalex.org/W2092633783","https://openalex.org/W2107076945","https://openalex.org/W2113754927","https://openalex.org/W2115002670","https://openalex.org/W2118929954","https://openalex.org/W2119722822","https://openalex.org/W2119785041","https://openalex.org/W2126256127","https://openalex.org/W2132035824","https://openalex.org/W2132758316","https://openalex.org/W2135120170","https://openalex.org/W2149724714","https://openalex.org/W2152567198","https://openalex.org/W2262860889","https://openalex.org/W2264331490","https://openalex.org/W2513293834","https://openalex.org/W3103781082","https://openalex.org/W3106440809","https://openalex.org/W3142834871","https://openalex.org/W4240739471","https://openalex.org/W4251386884","https://openalex.org/W6677973695","https://openalex.org/W6678190846","https://openalex.org/W6693154628","https://openalex.org/W6693634651"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W60786634","https://openalex.org/W1855765675","https://openalex.org/W3046859795","https://openalex.org/W1505902692","https://openalex.org/W2560894929","https://openalex.org/W2156524298","https://openalex.org/W2887888236","https://openalex.org/W2106942255","https://openalex.org/W1555620806"],"abstract_inverted_index":{"High-performance":[0],"and":[1,16,20,42,74,99,119,135,188],"low-power":[2],"computation":[3,44],"is":[4,162],"required":[5],"for":[6,31,40,76,129],"large-scale":[7],"fluid":[8,78],"dynamics":[9],"simulation.":[10],"Due":[11],"to":[12,46,64,102,124,182],"the":[13,32,67,105,126,131,136,166],"inefficient":[14],"architecture":[15,49,73],"structure":[17],"of":[18,158,165,169],"CPUs":[19],"GPUs,":[21],"they":[22],"now":[23],"have":[24],"a":[25,85,155],"difficulty":[26],"in":[27,114],"improving":[28],"power":[29],"efficiency":[30],"target":[33],"application.":[34],"Although":[35],"FPGAs":[36],"become":[37],"promising":[38],"alternatives":[39],"power-efficient":[41],"high-performance":[43],"due":[45],"their":[47,55],"new":[48],"having":[50],"floating-point":[51],"(FP)":[52],"DSP":[53],"blocks,":[54],"relatively":[56],"narrow":[57],"memory":[58],"bandwidth":[59,157],"requires":[60],"an":[61,72,115],"appropriate":[62],"way":[63],"fully":[65],"exploit":[66,89],"advantage.":[68],"This":[69],"paper":[70],"presents":[71],"design":[75,127],"scalable":[77],"simulation":[79],"based":[80],"on":[81],"data-flow":[82],"computing":[83],"with":[84,154],"state-of-the-art":[86],"FPGA.":[87],"To":[88],"available":[90],"hardware":[91],"resources":[92],"including":[93],"FP":[94],"DSPs,":[95],"we":[96],"introduce":[97],"spatial":[98,187],"temporal":[100,189],"parallelism":[101,190],"further":[103],"scale":[104,180],"performance":[106,168],"by":[107,185],"adding":[108],"more":[109],"stream":[110,156],"processing":[111],"elements":[112],"(SPEs)":[113],"array.":[116],"Performance":[117],"modeling":[118],"prototype":[120],"implementation":[121],"allow":[122],"us":[123],"explore":[125],"space":[128],"both":[130],"existing":[132],"Altera":[133],"Arria10":[134,144],"upcoming":[137],"Intel":[138],"Stratix10":[139,177],"FPGAs.":[140],"We":[141,173],"demonstrate":[142],"that":[143,176],"10AX115":[145],"FPGA":[146,178],"achieves":[147],"519":[148],"GFlops":[149,184],"at":[150],"9.67":[151],"GFlops/W":[152],"only":[153],"9.0":[159],"GB/s,":[160],"which":[161],"97.9":[163],"percent":[164],"peak":[167],"18":[170],"implemented":[171],"SPEs.":[172],"also":[174],"estimate":[175],"can":[179],"up":[181],"6844":[183],"combining":[186],"adequately.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}