Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
MRÁZEK, V. SEKANINA, L. VAŠÍČEK, Z.
Originální název
Using Libraries of Approximate Circuits in Design of Hardware Accelerators of Deep Neural Networks
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
Approximate circuits have been developed to provide good tradeoffs between power consumption and quality of service in error resilient applications such as hardware accelerators of deep neural networks (DNN). In order to accelerate the approximate circuit design process and to support a fair benchmarking of circuit approximation methods, libraries of approximate circuits have been introduced. For example, EvoApprox8b contains hundreds of 8-bit approximate adders and multipliers. By means of genetic programming we generated an extended version of the library in which thousands of 8- to 128-bit approximate arithmetic circuits are included. These circuits form Pareto fronts with respect to several error metrics, power consumption and other circuit parameters. In our case study we show how a large set of approximate multipliers can be used to perform a resilience analysis of a hardware accelerator of ResNet DNN and to select the most suitable approximate multiplier for a given application. Results are reported for various instances of the ResNet DNN trained on CIFAR-10 benchmark problem.
Klíčová slova
approximate circuit, genetic programming, convolutional neural network, hardware accelerator
Autoři
MRÁZEK, V.; SEKANINA, L.; VAŠÍČEK, Z.
Vydáno
30. 5. 2020
Nakladatel
Institute of Electrical and Electronics Engineers
Místo
Genoa
ISBN
978-1-7281-4922-6
Kniha
2nd IEEE International Conference on Artificial Intelligence Circuits and Systems
Strany od
243
Strany do
247
Strany počet
5
URL
https://arxiv.org/abs/2004.10483
BibTex
@inproceedings{BUT168115, author="Vojtěch {Mrázek} and Lukáš {Sekanina} and Zdeněk {Vašíček}", title="Using Libraries of Approximate Circuits in Design of Hardware Accelerators of Deep Neural Networks", booktitle="2nd IEEE International Conference on Artificial Intelligence Circuits and Systems", year="2020", pages="243--247", publisher="Institute of Electrical and Electronics Engineers", address="Genoa", doi="10.1109/AICAS48895.2020.9073837", isbn="978-1-7281-4922-6", url="https://arxiv.org/abs/2004.10483" }