{"id":"https://openalex.org/W3007527254","doi":"https://doi.org/10.1145/3373087.3375329","title":"DOMIS: Dual-Bank Optimal Micro-Architecture for Iterative Stencils","display_name":"DOMIS: Dual-Bank Optimal Micro-Architecture for Iterative Stencils","publication_year":2020,"publication_date":"2020-02-23","ids":{"openalex":"https://openalex.org/W3007527254","doi":"https://doi.org/10.1145/3373087.3375329","mag":"3007527254"},"language":"en","primary_location":{"id":"doi:10.1145/3373087.3375329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","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/A5013235794","display_name":"J. P. Escobedo","orcid":"https://orcid.org/0000-0003-2413-7119"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Juan Escobedo","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060908808","display_name":"Mingjie Lin","orcid":"https://orcid.org/0000-0002-3225-4406"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingjie Lin","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013235794"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0261324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"315","last_page":"315"},"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.9402322769165039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7951620817184448},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7120030522346497},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6760098934173584},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4997677803039551},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.495447039604187},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4937487542629242},{"id":"https://openalex.org/keywords/clock-rate","display_name":"Clock rate","score":0.48341357707977295},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.44917792081832886},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.43354976177215576},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.399527907371521},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3931238055229187},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34928905963897705},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.2819696366786957},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24502962827682495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07983121275901794}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9402322769165039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7951620817184448},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7120030522346497},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6760098934173584},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4997677803039551},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.495447039604187},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4937487542629242},{"id":"https://openalex.org/C178693496","wikidata":"https://www.wikidata.org/wiki/Q911691","display_name":"Clock rate","level":3,"score":0.48341357707977295},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.44917792081832886},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.43354976177215576},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.399527907371521},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3931238055229187},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34928905963897705},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2819696366786957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24502962827682495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07983121275901794},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","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},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3373087.3375329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3740958974","display_name":null,"funder_award_id":"1553056","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2564509292","https://openalex.org/W1795008753","https://openalex.org/W2336044659"],"abstract_inverted_index":{"High-Level":[0],"Synthesis":[1],"(HLS)":[2],"can":[3,34,51],"achieve":[4,67,91],"significant":[5],"performance":[6,152],"improvements":[7],"through":[8],"effective":[9],"memory":[10,71,161],"partitioning":[11],"and":[12,23,57,118,137],"meticulous":[13],"data":[14,167],"reuse.":[15],"Many":[16],"modern":[17],"applications,":[18],"such":[19],"as":[20],"medical":[21],"imaging":[22],"convolutional":[24],"layers":[25],"in":[26,126,147,179],"a":[27,112],"CNN,":[28],"mostly":[29],"contain":[30],"kernels":[31,124],"where":[32],"iterations":[33],"be":[35,52],"reordered":[36],"freely":[37],"without":[38],"compromising":[39],"its":[40],"correctness.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"an":[47,92],"optimal":[48],"micro-architecture":[49,107],"that":[50,61],"automatically":[53],"implemented":[54],"for":[55],"simple":[56],"iterative":[58],"stencil":[59,76,99],"computations":[60],"utilizes":[62],"only":[63,79],"2":[64],"banks":[65,162],"to":[66,86,90,164,183],"fully":[68],"parallel":[69],"conflict":[70],"accesses":[72,168],"from":[73],"single":[74],"stage":[75],"kernels,":[77],"while":[78,150],"requiring":[80],"reuse":[81],"buffers":[82],"of":[83,94,97,105,159],"size":[84,89],"proportional":[85],"the":[87,98,103,134,157],"kernel":[88],"II":[93],"1,":[95],"irrespectively":[96],"geometry.":[100],"We":[101],"demonstrate":[102],"effectiveness":[104],"our":[106,140],"by":[108,153,171],"implementing":[109],"it":[110,120],"with":[111,121,133,176],"Kintex":[113],"7":[114],"xc7k160tg676-1":[115],"Xilinx":[116],"FPGA":[117],"testing":[119],"several":[122],"stencil-based":[123],"found":[125],"real-world":[127],"applications.":[128],"On":[129],"average,":[130],"when":[131],"compared":[132],"mainstream":[135],"GMP":[136],"SRC":[138],"architectures":[139],"approach":[141],"achieves":[142],"approximately":[143],"30-":[144],"70%":[145],"reduction":[146],"hardware":[148],"usage,":[149],"improving":[151],"about":[154],"15%.":[155],"Moreover,":[156],"number":[158],"independent":[160],"required":[163],"accomplish":[165],"conflict-free":[166],"have":[169],"dropped":[170],"more":[172],"than":[173],"30%":[174],"together":[175],"some":[177],"increase":[178],"power":[180],"consumption":[181],"due":[182],"higher":[184],"clock":[185],"frequencies.":[186]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}