dc.contributor.author | Umuroglu, Yaman | |
dc.contributor.author | Fraser, Nicholas J. | |
dc.contributor.author | Gambardella, Giulio | |
dc.contributor.author | Blott, Michaela | |
dc.contributor.author | Leong, Philip W. | |
dc.contributor.author | Jahre, Magnus | |
dc.contributor.author | Vissers, Kees | |
dc.date.accessioned | 2018-02-01T10:19:52Z | |
dc.date.available | 2018-02-01T10:19:52Z | |
dc.date.created | 2017-02-17T16:14:26Z | |
dc.date.issued | 2017 | |
dc.identifier.isbn | 978-1-4503-4354-1 | |
dc.identifier.uri | http://hdl.handle.net/11250/2481166 | |
dc.description.abstract | Research 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.iso | eng | nb_NO |
dc.publisher | Association for Computing Machinery (ACM) | nb_NO |
dc.relation.ispartof | Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays | |
dc.relation.uri | http://www.idi.ntnu.no/~yamanu/2017-fpga-finn-preprint.pdf | |
dc.title | FINN: A Framework for Fast, Scalable Binarized Neural Network Inference | nb_NO |
dc.type | Chapter | nb_NO |
dc.description.version | acceptedVersion | nb_NO |
dc.source.pagenumber | 65-74 | nb_NO |
dc.identifier.cristin | 1451844 | |
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=3021744 | nb_NO |
cristin.unitcode | 194,63,10,0 | |
cristin.unitname | Institutt for datateknikk og informasjonsvitenskap | |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |