UNIVERSI
TÄ
TS-
BIBLIOTHEK
P
ADERBORN
Anmelden
Menü
Menü
Start
Hilfe
Blog
Weitere Dienste
Neuerwerbungslisten
Fachsystematik Bücher
Erwerbungsvorschlag
Bestellung aus dem Magazin
Fernleihe
Einstellungen
Sprache
Deutsch
Deutsch
Englisch
Farbschema
Hell
Dunkel
Automatisch
Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist
gegebenenfalls
nur via VPN oder Shibboleth (DFN-AAI) möglich.
mehr Informationen...
Universitätsbibliothek
Katalog
Suche
Details
Zur Ergebnisliste
Ergebnis 13 von 1008
Datensatz exportieren als...
BibTeX
FPGA‐accelerated deep convolutional neural networks for high throughput and energy efficiency
Concurrency and computation, 2017-10, Vol.29 (20), p.n/a
Qiao, Yuran
Shen, Junzhong
Xiao, Tao
Yang, Qianming
Wen, Mei
Zhang, Chunyuan
2017
Volltextzugriff (PDF)
Details
Autor(en) / Beteiligte
Qiao, Yuran
Shen, Junzhong
Xiao, Tao
Yang, Qianming
Wen, Mei
Zhang, Chunyuan
Titel
FPGA‐accelerated deep convolutional neural networks for high throughput and energy efficiency
Ist Teil von
Concurrency and computation, 2017-10, Vol.29 (20), p.n/a
Ort / Verlag
Hoboken: Wiley Subscription Services, Inc
Erscheinungsjahr
2017
Quelle
Wiley Online Library
Beschreibungen/Notizen
Summary Recent breakthroughs in the deep convolutional neural networks (CNNs) have led to great improvements in the accuracy of both vision and auditory systems. Characterized by their deep structures and large numbers of parameters, deep CNNs challenge the computational performance of today. Hardware specialization in the form of field‐programmable gate array offers a promising path towards major leaps in computational performance while achieving high‐energy efficiency. In this paper, we focus on accelerating deep CNNs using the Xilinx Zynq‐zq7045 FPGA SoC. As most of the computational workload can be converted to matrix multiplications, we adopt a matrix multiplier‐based accelerator architecture. Dedicated units are designed to eliminate the conversion overhead. We also design a customized memory system according to the memory access pattern of CNNs. To make the accelerator easily usable by application developers, our accelerator supports Caffe, which is a widely used software framework of deep CNN. Different CNN models can be adopted by our accelerator, with good performance portability. The experimental results show that for a typical application of CNN, image classification, an average throughout of 77.8 GFLOPS is achieved, while the energy efficiency is 4.7× better than an Nvidia K20 GPGPU. © 2016 The Authors. Concurrency and Computation: Practice and Experience Published by John Wiley & Sons Ltd
Sprache
Englisch
Identifikatoren
ISSN: 1532-0626
eISSN: 1532-0634
DOI: 10.1002/cpe.3850
Titel-ID: cdi_proquest_journals_1941166030
Format
–
Schlagworte
Accelerator
,
Artificial neural networks
,
Caffe
,
CNN
,
Computer memory
,
Computing time
,
Concurrency
,
Customization
,
Energy conversion efficiency
,
Energy efficiency
,
Field programmable gate arrays
,
FPGA
,
Image classification
,
Matrix Multiplier
,
Neural networks
Weiterführende Literatur
Empfehlungen zum selben Thema automatisch vorgeschlagen von
bX