Publication detail

Libraries of Approximate Circuits: Automated Design and Application in CNN Accelerators

MRÁZEK, V. SEKANINA, L. VAŠÍČEK, Z.

Original Title

Libraries of Approximate Circuits: Automated Design and Application in CNN Accelerators

Type

journal article in Web of Science

Language

English

Original Abstract

Libraries of approximate circuits are composed of fully characterized digital circuits that can be used as building blocks of energy-efficient implementations of hardware accelerators. They can be employed not only to speed up the accelerator development but also to analyze how an accelerator responds to introducing various approximate operations. In this paper, we present a methodology that automatically builds comprehensive libraries of approximate circuits with desired properties. Target approximate circuits are generated using Cartesian genetic programming. In addition to extending the EvoApprox8b library that contains common approximate arithmetic circuits, we show how to generate more specific approximate circuits; in particular, MxN-bit approximate multipliers that exhibit promising results when deployed in convolutional neural networks. By means of the evolved approximate multipliers, we perform a detailed error resilience analysis of five different ResNet networks. We identify the convolutional layers that are good candidates for adopting the approximate multipliers and suggest particular approximate multipliers whose application can lead to the best trade-offs between the classification accuracy and energy requirements. Experiments are reported for CIFAR-10 and CIFAR-100 data sets.

Keywords

approximate circuit, genetic programming, convolutional neural network, hardware accelerator, optimization

Authors

MRÁZEK, V.; SEKANINA, L.; VAŠÍČEK, Z.

Released

14. 12. 2020

ISBN

2156-3357

Periodical

IEEE Journal on Emerging and Selected Topics in Circuits and Systems

Year of study

10

Number

4

State

United States of America

Pages from

406

Pages to

418

Pages count

13

URL

https://www.fit.vut.cz/research/publication/12372/

BibTex

@article{BUT168178,
  author="Vojtěch {Mrázek} and Lukáš {Sekanina} and Zdeněk {Vašíček}",
  title="Libraries of Approximate Circuits: Automated Design and Application in CNN Accelerators",
  journal="IEEE Journal on Emerging and Selected Topics in Circuits and Systems",
  year="2020",
  volume="10",
  number="4",
  pages="406--418",
  doi="10.1109/JETCAS.2020.3032495",
  issn="2156-3357",
  url="https://www.fit.vut.cz/research/publication/12372/"
}