{"id":"https://openalex.org/W4312599008","doi":"https://doi.org/10.1145/3549206.3549322","title":"End to End Framework for CNN Acceleration on FPGAs with Dynamic Algorithm Mapping","display_name":"End to End Framework for CNN Acceleration on FPGAs with Dynamic Algorithm Mapping","publication_year":2022,"publication_date":"2022-08-04","ids":{"openalex":"https://openalex.org/W4312599008","doi":"https://doi.org/10.1145/3549206.3549322"},"language":"en","primary_location":{"id":"doi:10.1145/3549206.3549322","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549206.3549322","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549206.3549322","source":{"id":"https://openalex.org/S4363609025","display_name":"Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3549206.3549322","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032056932","display_name":"Haomei Liu","orcid":"https://orcid.org/0000-0003-2475-8134"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haomei Liu","raw_affiliation_strings":["Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050528589","display_name":"Yuan Meng","orcid":"https://orcid.org/0000-0001-6468-8623"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Meng","raw_affiliation_strings":["Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015036207","display_name":"Sanmukh R. Kuppannagari","orcid":"https://orcid.org/0000-0002-2062-1483"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanmukh Rao Kuppannagari","raw_affiliation_strings":["Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033166029","display_name":"Viktor K. Prasanna","orcid":"https://orcid.org/0000-0002-1609-8589"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor K. Prasanna","raw_affiliation_strings":["Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"696","last_page":"700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9947999715805054,"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":0.8527679443359375},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8148599863052368},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6361138820648193},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.608444333076477},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5765063166618347},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5516470670700073},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5461531281471252},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5181738138198853},{"id":"https://openalex.org/keywords/high-level-synthesis","display_name":"High-level synthesis","score":0.4873007535934448},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4757528007030487},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43525418639183044},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4323233962059021},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.43089112639427185},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.429067462682724},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.40379300713539124},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39195334911346436},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37617409229278564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20283243060112},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1975286602973938},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15954139828681946},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09357070922851562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8527679443359375},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8148599863052368},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6361138820648193},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.608444333076477},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5765063166618347},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5516470670700073},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5461531281471252},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5181738138198853},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.4873007535934448},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4757528007030487},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43525418639183044},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4323233962059021},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.43089112639427185},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.429067462682724},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.40379300713539124},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39195334911346436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37617409229278564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20283243060112},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1975286602973938},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15954139828681946},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09357070922851562},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3549206.3549322","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549206.3549322","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549206.3549322","source":{"id":"https://openalex.org/S4363609025","display_name":"Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3549206.3549322","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549206.3549322","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549206.3549322","source":{"id":"https://openalex.org/S4363609025","display_name":"Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G3757289616","display_name":"CNS Core: Small: AccelRITE: Accelerating ReInforcemenT Learning based  AI at the Edge Using FPGAs","funder_award_id":"2009057","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6237556090","display_name":null,"funder_award_id":"CNS-2009057","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6656871041","display_name":"SaTC: CORE: Small: Accelerating Privacy Preserving Deep Learning for Real-time Secure Applications","funder_award_id":"2104264","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7383255365","display_name":"Collaborative Research:PPoSS:Planning: Streamware - A Scalable Framework for Accelerating Streaming Data Science","funder_award_id":"2119816","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312599008.pdf","grobid_xml":"https://content.openalex.org/works/W4312599008.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1993830291","https://openalex.org/W2183341477","https://openalex.org/W3034971973","https://openalex.org/W3091969046","https://openalex.org/W3110305433","https://openalex.org/W3129894558","https://openalex.org/W4206902753","https://openalex.org/W4214633034","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W107105315","https://openalex.org/W1584537303","https://openalex.org/W4388155270","https://openalex.org/W1872724644","https://openalex.org/W4367156293","https://openalex.org/W2750549761","https://openalex.org/W28826848","https://openalex.org/W2122272819","https://openalex.org/W2994151208","https://openalex.org/W4383749428"],"abstract_inverted_index":{"As":[0],"CNNs":[1],"are":[2,18],"becoming":[3],"more":[4],"diverse":[5],"with":[6,82],"respect":[7],"to":[8,20,87,108,126,131],"per-layer":[9,12],"computation":[10],"characteristics,":[11],"strategy":[13],"selection":[14],"and":[15,36,54,76],"fine-grained":[16],"tuning":[17],"required":[19],"achieve":[21,132],"low":[22,138],"end-to-end":[23,43],"latency.":[24],"DYNAMAP":[25,46,86],"is":[26,124],"a":[27,38],"framework":[28,123],"for":[29,33,63,105],"efficiently":[30],"selecting":[31],"algorithms":[32],"different":[34],"layers":[35],"re-using":[37],"unified":[39],"accelerator.":[40],"However,":[41],"the":[42,66,83,98,110,141],"deployment":[44,142],"of":[45,52,85,97,112],"faces":[47],"some":[48],"challenges":[49],"in":[50,140],"terms":[51],"productivity":[53,111],"portability.":[55,90],"In":[56],"this":[57,81],"work,":[58],"we":[59,119],"develop":[60],"an":[61,94],"API":[62],"automatically":[64,127],"extracting":[65],"ONNX":[67],"graph":[68],"from":[69],"high-level":[70],"programming":[71],"libraries":[72],"such":[73],"as":[74],"Pytorch":[75],"Tensorflow.":[77],"We":[78,91],"further":[79],"integrate":[80],"front-end":[84],"increase":[88,109],"its":[89],"then":[92],"define":[93],"HLS":[95],"template":[96],"accelerator":[99],"supporting":[100],"three":[101,116],"parallel":[102],"algorithm":[103],"choices":[104],"convolution":[106],"operations":[107],"generating":[113],"hardware.":[114],"Using":[115],"state-of-the-art":[117],"CNNs,":[118],"demonstrate":[120],"that":[121],"our":[122],"able":[125],"deploy":[128],"CNN":[129],"models":[130],"minimum":[133],"latency":[134],"which":[135],"incurs":[136],"very":[137],"overhead":[139],"process.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}