{"id":"https://openalex.org/W2787249700","doi":"https://doi.org/10.1109/fpt.2017.8280119","title":"SMEFF: A scalable memory extension fabric for FPGA","display_name":"SMEFF: A scalable memory extension fabric for FPGA","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787249700","doi":"https://doi.org/10.1109/fpt.2017.8280119","mag":"2787249700"},"language":"en","primary_location":{"id":"doi:10.1109/fpt.2017.8280119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2017.8280119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Field Programmable Technology (ICFPT)","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/A5034949655","display_name":"Li Wei","orcid":"https://orcid.org/0000-0003-2453-2055"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Li","raw_affiliation_strings":["Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694861","display_name":"Yangyang Zhao","orcid":"https://orcid.org/0000-0003-1937-9412"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Zhao","raw_affiliation_strings":["Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420964","display_name":"Yuhang Liu","orcid":"https://orcid.org/0000-0002-5784-3581"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Liu","raw_affiliation_strings":["Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101645579","display_name":"Mingyu Chen","orcid":"https://orcid.org/0000-0003-4469-1037"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Chen","raw_affiliation_strings":["Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034949655"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22228837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":null,"first_page":"40","last_page":"47"},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.8212594985961914},{"id":"https://openalex.org/keywords/registered-memory","display_name":"Registered memory","score":0.6713722944259644},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.6430572271347046},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5896912217140198},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5842257738113403},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5815999507904053},{"id":"https://openalex.org/keywords/memory-refresh","display_name":"Memory refresh","score":0.538749098777771},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5284331440925598},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.5172896385192871},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.48990529775619507},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.4213169813156128},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.41752102971076965},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.41705214977264404},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3270074725151062},{"id":"https://openalex.org/keywords/computer-memory","display_name":"Computer memory","score":0.2493915855884552},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11664769053459167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212594985961914},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.6713722944259644},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.6430572271347046},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5896912217140198},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5842257738113403},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5815999507904053},{"id":"https://openalex.org/C87907426","wikidata":"https://www.wikidata.org/wiki/Q6815755","display_name":"Memory refresh","level":4,"score":0.538749098777771},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5284331440925598},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.5172896385192871},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.48990529775619507},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.4213169813156128},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.41752102971076965},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.41705214977264404},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3270074725151062},{"id":"https://openalex.org/C92855701","wikidata":"https://www.wikidata.org/wiki/Q5830907","display_name":"Computer memory","level":3,"score":0.2493915855884552},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11664769053459167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpt.2017.8280119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2017.8280119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Field Programmable Technology (ICFPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1969720574","https://openalex.org/W1981770094","https://openalex.org/W2000992769","https://openalex.org/W2080251468","https://openalex.org/W2082289230","https://openalex.org/W2102449048","https://openalex.org/W2124064997","https://openalex.org/W2127703947","https://openalex.org/W2156094106","https://openalex.org/W2157554053","https://openalex.org/W2294793262","https://openalex.org/W2724920573","https://openalex.org/W2731118616","https://openalex.org/W3101420126","https://openalex.org/W3152304157","https://openalex.org/W4251433554","https://openalex.org/W4254778370"],"related_works":["https://openalex.org/W2354036839","https://openalex.org/W2044064773","https://openalex.org/W2587873888","https://openalex.org/W2155373950","https://openalex.org/W3048967625","https://openalex.org/W1575240748","https://openalex.org/W4248614727","https://openalex.org/W2296275612","https://openalex.org/W2612506697","https://openalex.org/W2782503170"],"abstract_inverted_index":{"In":[0,37],"resource-constrained":[1],"FPGA":[2,98],"systems,":[3,227],"off-chip":[4],"memory":[5,42,104,116,127,152,189,212,219,226,257,264,282],"plays":[6],"an":[7,102,143,195],"important":[8],"role":[9],"in":[10],"both":[11],"prototype":[12,53,197,263],"verification":[13,54],"and":[14,28,44,50,56,83,107,118,129,132,136,183,215,228,245,267],"acceleration":[15,57],"systems":[16,55,265],"for":[17,97,275],"big":[18],"data.":[19],"As":[20],"the":[21,30,48,113,134,156,163,181,200,276],"scale":[22,49],"of":[23,52,69,115,138,155,185,202,235,247,278],"applications":[24],"become":[25],"increasingly":[26],"large":[27],"complex,":[29],"data":[31,60,73,139,176,186,233],"to":[32,64,111,125,148,161,172,198,217,223,241,249,254],"be":[33,65],"processed":[34],"grows":[35],"exponentially.":[36],"contrast,":[38],"FPGAs":[39],"provide":[40],"limited":[41],"capacity":[43,117,128,213,266],"bandwidth,":[45],"severely":[46],"limiting":[47],"performance":[51,82],"systems.":[58,231,258],"Furthermore,":[59],"movement":[61,74,177,187,234],"is":[62,101,142,169],"expected":[63],"a":[66,89,150,170],"dominant":[67],"consumer":[68],"energy,":[70],"thus":[71,260],"inefficient":[72],"between":[75,188],"different":[76],"DRAM":[77],"modules":[78],"also":[79],"incurs":[80],"significant":[81],"energy":[84,251],"penalties.":[85],"This":[86],"paper":[87],"proposes":[88],"practical":[90],"design:":[91],"A":[92],"Scalable":[93],"Memory":[94],"Extension":[95],"Fabric":[96],"(SMEFF),":[99],"which":[100,179],"asynchronous":[103],"access":[105],"mechanism":[106,160],"exploits":[108],"cascaded":[109],"technology":[110,238],"solve":[112,162],"problem":[114],"bandwidth.":[119,268],"SMEFF":[120,193,209,259],"uses":[121],"two":[122],"key":[123],"technologies":[124],"achieve":[126],"bandwidth":[130,220],"improvements,":[131],"shrink":[133],"latency":[135,182,243],"overhead":[137,184],"movement-the":[140],"first":[141],"FPGA-based":[144,196,225,256,262,281],"high-speed":[145],"serial":[146],"bus":[147,159],"build":[149],"multi-level":[151],"fabric":[153],"instead":[154],"traditional":[157],"parallel":[158],"signal":[164],"integrity":[165],"problem.":[166],"The":[167,232],"second":[168],"module":[171,173],"(M-To-M)":[174],"DMA":[175,237],"technology,":[178],"reduces":[180],"modules.":[190],"We":[191],"implement":[192],"on":[194],"demonstrate":[199],"feasibility":[201],"our":[203,271],"approach.":[204],"Experimental":[205],"results":[206],"show":[207],"that":[208],"provides":[210,273],"5x":[211],"increase":[214],"up":[216,240],"3.6x":[218],"improvement":[221],"compared":[222,253],"state-of-the-art":[224,255],"outperforms":[229],"PCIe-based":[230],"M-TO-M's":[236],"obtains":[239],"3x":[242],"reduction,":[244],"average":[246],"21.1%":[248],"61.1%":[250],"reduction":[252],"increases":[261],"More":[269],"importantly,":[270],"architecture":[272],"opportunities":[274],"design":[277],"scalable,":[279],"cost-effective":[280],"subsystems.":[283]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}