{"id":"https://openalex.org/W2794535120","doi":"https://doi.org/10.3906/elk-1706-222","title":"Optimizing FPGA-based CNN accelerator for energy efficiency with an extended Roofline model","display_name":"Optimizing FPGA-based CNN accelerator for energy efficiency with an extended Roofline model","publication_year":2018,"publication_date":"2018-03-30","ids":{"openalex":"https://openalex.org/W2794535120","doi":"https://doi.org/10.3906/elk-1706-222","mag":"2794535120"},"language":"en","primary_location":{"id":"doi:10.3906/elk-1706-222","is_oa":true,"landing_page_url":"https://doi.org/10.3906/elk-1706-222","pdf_url":"https://doi.org/10.3906/elk-1706-222","source":{"id":"https://openalex.org/S32837994","display_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES","issn_l":"1300-0632","issn":["1300-0632","1303-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318422","host_organization_name":"Scientific and Technological Research Council of Turkey (TUBITAK)","host_organization_lineage":["https://openalex.org/P4310318422"],"host_organization_lineage_names":["Scientific and Technological Research Council of Turkey (TUBITAK)"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING &amp; COMPUTER SCIENCES","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.3906/elk-1706-222","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076653747","display_name":"Sayed Omid Ayat","orcid":"https://orcid.org/0000-0003-1351-4599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"SAYED OMID AYAT","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083733149","display_name":"Mohamed Khalil-Hani","orcid":"https://orcid.org/0000-0002-2375-5719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MOHAMED KHALIL-HANI","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026822024","display_name":"Ab Al-Hadi Ab Rahman","orcid":"https://orcid.org/0000-0002-0754-5199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"AB AL-HADI AB RAHMAN","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.212,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.53603708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"26","issue":"2","first_page":"919","last_page":"935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9987000226974487,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.8131324052810669},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8010425567626953},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6594843864440918},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6337392330169678},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6182833313941956},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6120162010192871},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5488782525062561},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.456400066614151},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.43056023120880127},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41242337226867676},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.369385302066803},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35054928064346313},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34606051445007324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19256410002708435},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08573076128959656},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08277416229248047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131324052810669},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8010425567626953},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6594843864440918},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6337392330169678},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6182833313941956},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6120162010192871},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5488782525062561},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.456400066614151},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.43056023120880127},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41242337226867676},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.369385302066803},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35054928064346313},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34606051445007324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19256410002708435},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08573076128959656},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08277416229248047},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3906/elk-1706-222","is_oa":true,"landing_page_url":"https://doi.org/10.3906/elk-1706-222","pdf_url":"https://doi.org/10.3906/elk-1706-222","source":{"id":"https://openalex.org/S32837994","display_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES","issn_l":"1300-0632","issn":["1300-0632","1303-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318422","host_organization_name":"Scientific and Technological Research Council of Turkey (TUBITAK)","host_organization_lineage":["https://openalex.org/P4310318422"],"host_organization_lineage_names":["Scientific and Technological Research Council of Turkey (TUBITAK)"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING &amp; COMPUTER SCIENCES","raw_type":"journal-article"},{"id":"pmh:oai:dergipark.org.tr:article/573022","is_oa":false,"landing_page_url":"https://dergipark.org.tr/tr/pub/tbtkelektrik/issue/45586/573022","pdf_url":null,"source":{"id":"https://openalex.org/S4306401840","display_name":"DergiPark (Istanbul University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67581229","host_organization_name":"Istanbul University","host_organization_lineage":["https://openalex.org/I67581229"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"\\n                                                                    Volume: 26, Issue: 2\\n                                                                                                    919-935\\n                                                                \\n                            ","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3906/elk-1706-222","is_oa":true,"landing_page_url":"https://doi.org/10.3906/elk-1706-222","pdf_url":"https://doi.org/10.3906/elk-1706-222","source":{"id":"https://openalex.org/S32837994","display_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES","issn_l":"1300-0632","issn":["1300-0632","1303-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318422","host_organization_name":"Scientific and Technological Research Council of Turkey (TUBITAK)","host_organization_lineage":["https://openalex.org/P4310318422"],"host_organization_lineage_names":["Scientific and Technological Research Council of Turkey (TUBITAK)"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING &amp; COMPUTER SCIENCES","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4313341326","https://openalex.org/W4282568311","https://openalex.org/W4313484792","https://openalex.org/W2951473296","https://openalex.org/W2883928845","https://openalex.org/W4288420200","https://openalex.org/W4285346947","https://openalex.org/W3145095675","https://openalex.org/W4365793791","https://openalex.org/W3134072570"],"abstract_inverted_index":{"In":[0,109,183],"recent":[1],"years,":[2],"the":[3,33,45,49,53,58,73,85,88,95,121,126,130,137,142,149,163,170,187,192,214,235,239],"convolutional":[4],"neural":[5],"network":[6],"(CNN)":[7],"has":[8,38,191],"found":[9],"wide":[10],"acceptance":[11],"in":[12,48,94,153,176,221],"solving":[13],"practical":[14,65],"computer":[15],"vision":[16],"and":[17,30,81,181,203,258],"image":[18],"recognition":[19,66],"problems.":[20],"Also":[21],"recently,":[22],"due":[23],"to":[24,43,56,78,104,178,185,227,232],"its":[25],"flexibility,":[26],"faster":[27],"development":[28],"time,":[29],"energy":[31,194,201,211,236,259],"efficiency,":[32,195],"field-programmable":[34],"gate":[35],"array":[36],"(FPGA)":[37],"become":[39],"an":[40,145],"attractive":[41],"solution":[42,189,207],"exploit":[44],"inherent":[46],"parallelism":[47],"feedforward":[50],"process":[51],"of":[52,63,75,84,90,129,144,148,162,210,238,255,261],"CNN.":[54],"However,":[55],"meet":[57],"demands":[59],"for":[60],"high":[61],"accuracy":[62],"today&amp;#039;s":[64],"applications":[67],"that":[68,118,190,246],"typically":[69],"have":[70,77],"massive":[71],"datasets,":[72],"sizes":[74],"CNNs":[76],"be":[79],"larger":[80],"deeper.":[82],"Enlargement":[83],"CNN":[86,241,248],"aggravates":[87],"problem":[89],"off-chip":[91,122],"memory":[92,115,123,159],"bottleneck":[93],"FPGA":[96,268],"platform":[97],"since":[98,169],"there":[99],"is":[100],"not":[101],"enough":[102],"space":[103],"save":[105],"large":[106],"datasets":[107],"on-chip.":[108],"this":[110,154],"work,":[111,155],"we":[112,156,196],"propose":[113,226],"a":[114,198,229,252,265],"system":[116,164],"architecture":[117],"best":[119,193],"matches":[120],"traffic":[124],"with":[125,213],"optimum":[127],"throughput":[128,222],"computation":[131],"engine,":[132],"while":[133],"it":[134],"operates":[135],"at":[136,165,271],"maximum":[138],"allowable":[139],"frequency.":[140],"With":[141],"help":[143],"extended":[146],"version":[147],"Roofline":[150],"model":[151,172],"proposed":[152,171],"can":[157,250],"estimate":[158],"bandwidth":[160,179],"utilization":[161,180,212],"different":[166],"operating":[167,174],"frequencies":[168],"considers":[173],"frequency":[175],"addition":[177],"throughput.":[182,205],"order":[184],"find":[186],"optimal":[188],"make":[197],"trade-off":[199,215],"between":[200],"efficiency":[202,237,260],"computational":[204],"This":[206],"saves":[208],"18%":[209],"having":[216],"less":[217],"than":[218],"2%":[219],"reduction":[220],"performance.":[223],"We":[224],"also":[225],"use":[228],"race-to-halt":[230],"strategy":[231],"further":[233],"improve":[234],"designed":[240],"accelerator.":[242],"Experimental":[243],"results":[244],"show":[245],"our":[247],"accelerator":[249],"achieve":[251],"peak":[253],"performance":[254],"52.11":[256],"GFLOPS":[257],"10.02":[262],"GFLOPS/W":[263],"on":[264],"ZYNQ":[266],"ZC706":[267],"board":[269],"running":[270],"250":[272],"MHz,":[273],"which":[274],"outperforms":[275],"most":[276],"previous":[277],"approaches.":[278]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
