Show simple item record

dc.contributor.authorUmuroglu, Yaman
dc.contributor.authorFraser, Nicholas J.
dc.contributor.authorGambardella, Giulio
dc.contributor.authorBlott, Michaela
dc.contributor.authorLeong, Philip W.
dc.contributor.authorJahre, Magnus
dc.contributor.authorVissers, Kees
dc.date.accessioned2018-02-01T10:19:52Z
dc.date.available2018-02-01T10:19:52Z
dc.date.created2017-02-17T16:14:26Z
dc.date.issued2017
dc.identifier.isbn978-1-4503-4354-1
dc.identifier.urihttp://hdl.handle.net/11250/2481166
dc.description.abstractResearch has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values. In this paper, we present FINN, a framework for building fast and flexible FPGA accelerators using a flexible heterogeneous streaming architecture. By utilizing a novel set of optimizations that enable efficient mapping of binarized neural networks to hardware, we implement fully connected, convolutional and pooling layers, with per-layer compute resources being tailored to user-provided throughput requirements. On a ZC706 embedded FPGA platform drawing less than 25 W total system power, we demonstrate up to 12.3 million image classifications per second with 0.31 μs latency on the MNIST dataset with 95.8% accuracy, and 21906 image classifications per second with 283 μs latency on the CIFAR-10 and SVHN datasets with respectively 80.1% and 94.9% accuracy. To the best of our knowledge, ours are the fastest classification rates reported to date on these benchmarks.nb_NO
dc.language.isoengnb_NO
dc.publisherAssociation for Computing Machinery (ACM)nb_NO
dc.relation.ispartofProceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays
dc.relation.urihttp://www.idi.ntnu.no/~yamanu/2017-fpga-finn-preprint.pdf
dc.titleFINN: A Framework for Fast, Scalable Binarized Neural Network Inferencenb_NO
dc.typeChapternb_NO
dc.description.versionacceptedVersionnb_NO
dc.source.pagenumber65-74nb_NO
dc.identifier.cristin1451844
dc.description.localcode© ACM, 2017. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM Transactions of Computing Education, https://dl.acm.org/citation.cfm?id=3021744nb_NO
cristin.unitcode194,63,10,0
cristin.unitnameInstitutt for datateknikk og informasjonsvitenskap
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record