{"id":"https://openalex.org/W3043884287","doi":"https://doi.org/10.48550/arxiv.2007.10451","title":"HPIPE: Heterogeneous Layer-Pipelined and Sparse-Aware CNN Inference for FPGAs","display_name":"HPIPE: Heterogeneous Layer-Pipelined and Sparse-Aware CNN Inference for FPGAs","publication_year":2020,"publication_date":"2020-07-20","ids":{"openalex":"https://openalex.org/W3043884287","doi":"https://doi.org/10.48550/arxiv.2007.10451","mag":"3043884287"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2007.10451","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10451","pdf_url":"https://arxiv.org/pdf/2007.10451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.10451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075413522","display_name":"Mathew Hall","orcid":"https://orcid.org/0000-0002-2134-8247","observed_orcids":["https://orcid.org/0000-0002-2134-8247"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hall, Mathew","raw_affiliation_strings":["Department of Electrical and Computer Engineering , University of Toronto Toronto , Canada","University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , University of Toronto Toronto , Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030184404","display_name":"Vaughn Betz","orcid":"https://orcid.org/0000-0003-0528-6493","observed_orcids":["https://orcid.org/0000-0003-0528-6493"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Betz, Vaughn","raw_affiliation_strings":["Department of Electrical and Computer Engineering , University of Toronto Toronto , Canada","University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , University of Toronto Toronto , Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6338000297546387,"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":0.6338000297546387,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.34470000863075256,"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/T13292","display_name":"Embedded Systems and FPGA Applications","score":0.004699999932199717,"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/cnn-accelerator","display_name":"CNN accelerator","score":0.7049999833106995},{"id":"https://openalex.org/keywords/fpga","display_name":"FPGA","score":0.8519999980926514},{"id":"https://openalex.org/keywords/resnet-50","display_name":"ResNet50","score":0.7789999842643738},{"id":"https://openalex.org/keywords/mobilenet","display_name":"MobileNet","score":0.9909999966621399},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.6890000104904175},{"id":"https://openalex.org/keywords/throughput","display_name":"throughput","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8558740019798279},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.7684739828109741},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7619671821594238},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6085329055786133},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5823991894721985},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5525951385498047},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5196112990379333},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5018270015716553},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.46769073605537415},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.4418385922908783},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3692460060119629},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.335232675075531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26273617148399353},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09433558583259583},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2007.10451","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10451","pdf_url":"https://arxiv.org/pdf/2007.10451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3043884287","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.10451.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2007.10451","doi":"https://doi.org/10.48550/arxiv.2007.10451","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.10451","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.10451","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10451","pdf_url":"https://arxiv.org/pdf/2007.10451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3043884287.pdf","grobid_xml":"https://content.openalex.org/works/W3043884287.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2285660444","https://openalex.org/W2565851976","https://openalex.org/W2584616277","https://openalex.org/W2585720638","https://openalex.org/W2623629680","https://openalex.org/W2707890836","https://openalex.org/W2751477244","https://openalex.org/W2809121165","https://openalex.org/W2827334269","https://openalex.org/W2883929540","https://openalex.org/W2900228909","https://openalex.org/W2904795057","https://openalex.org/W2915106038","https://openalex.org/W2916778556","https://openalex.org/W2917087921","https://openalex.org/W2918817571","https://openalex.org/W2946948417","https://openalex.org/W2949619037","https://openalex.org/W2989331028"],"related_works":["https://openalex.org/W3118577016","https://openalex.org/W3161204726","https://openalex.org/W7138268896","https://openalex.org/W2949619037","https://openalex.org/W2982309957","https://openalex.org/W3129147932","https://openalex.org/W2883927138","https://openalex.org/W2997828269","https://openalex.org/W4405272042","https://openalex.org/W4328012083"],"abstract_inverted_index":{"We":[0,100,122],"present":[1],"both":[2,108],"a":[3,12,34,52,117,132],"novel":[4],"Convolutional":[5],"Neural":[6],"Network":[7],"(CNN)":[8],"accelerator":[9,77],"architecture":[10,106],"and":[11,44,69,83,111,155],"network":[13,37],"compiler":[14,38],"for":[15,48,57],"FPGAs":[16],"that":[17,28,124],"outperforms":[18,156],"all":[19,157],"prior":[20,92,158],"work.":[21],"Instead":[22],"of":[23,51,91,104,135,137,146],"having":[24],"generic":[25],"processing":[26],"elements":[27],"together":[29],"process":[30],"one":[31],"layer":[32,50,59],"at":[33,85,131],"time,":[35],"our":[36,63,76,105],"statically":[39],"partitions":[40],"available":[41],"device":[42],"resources":[43],"builds":[45],"custom-tailored":[46],"hardware":[47,56],"each":[49,58],"CNN.":[53],"By":[54],"building":[55],"we":[60],"can":[61],"pack":[62],"controllers":[64],"into":[65],"fewer":[66],"lookup":[67],"tables":[68],"use":[70],"dedicated":[71],"routing.":[72],"These":[73],"efficiencies":[74],"enable":[75],"to":[78],"utilize":[79],"2x":[80,88],"the":[81,89,102,125,144,153],"DSPs":[82],"operate":[84],"more":[86],"than":[87],"frequency":[90],"work":[93,159],"on":[94,98,107,116,160],"sparse":[95,109,126],"CNN":[96],"acceleration":[97],"FPGAs.":[99,161],"evaluate":[101],"performance":[103],"Resnet-50":[110,127],"dense":[112],"MobileNet":[113],"Imagenet":[114],"classifiers":[115],"Stratix":[118],"10":[119],"2800":[120],"FPGA.":[121],"find":[123],"model":[128],"has":[129],"throughput":[130,145],"batch":[133],"size":[134],"1":[136],"4550":[138],"images/s,":[139],"which":[140],"is":[141],"nearly":[142],"4x":[143],"NVIDIA's":[147],"fastest":[148],"machine":[149],"learning":[150],"targeted":[151],"GPU,":[152],"V100,":[154]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-07-29T00:00:00"}