Detail publikace

ApproxFPGAs: Embracing ASIC-based Approximate Arithmetic Components for FPGA-Based Systems

PRABAKARAN, B. MRÁZEK, V. VAŠÍČEK, Z. SEKANINA, L. SHAFIQUE, M.

Originální název

ApproxFPGAs: Embracing ASIC-based Approximate Arithmetic Components for FPGA-Based Systems

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

There has been abundant research on the development of Approximate Circuits (ACs) for ASICs. However, previous studies have illustrated that ASIC-based ACs offer asymmetrical gains in FPGA-based accelerators. Therefore, an AC that might be pareto-optimal for ASICs might not be pareto-optimal for FPGAs. In this work, we present the ApproxFPGAs methodology that uses machine learning models to reduce the exploration time for analyzing the state-of-the-art ASIC-based ACs to determine the set of pareto-optimal FPGA-based ACs. We also perform a case-study to illustrate the benefits obtained by deploying these pareto-optimal FPGA-ACs in a state-of-the-art automation framework to systematically generate pareto-optimal approximate accelerators that can be deployed in FPGA-based systems to achieve high performance or low-power consumption.

Klíčová slova

Approximate Computing, FPGA, ASIC, Adder, Multiplier, Arithmetic Units, Machine Learning 

Autoři

PRABAKARAN, B.; MRÁZEK, V.; VAŠÍČEK, Z.; SEKANINA, L.; SHAFIQUE, M.

Vydáno

19. 7. 2020

Nakladatel

Institute of Electrical and Electronics Engineers

Místo

San Francisco

ISBN

978-1-4503-6725-7

Kniha

2020 57th ACM/IEEE Design Automation Conference (DAC)

Strany od

1

Strany do

6

Strany počet

6

URL

https://arxiv.org/abs/2004.10502

BibTex

@inproceedings{BUT168121,
  author="PRABAKARAN, B. and MRÁZEK, V. and VAŠÍČEK, Z. and SEKANINA, L. and SHAFIQUE, M.",
  title="ApproxFPGAs: Embracing ASIC-based Approximate Arithmetic Components for FPGA-Based Systems",
  booktitle="2020 57th ACM/IEEE Design Automation Conference (DAC)",
  year="2020",
  pages="1--6",
  publisher="Institute of Electrical and Electronics Engineers",
  address="San Francisco",
  doi="10.1109/DAC18072.2020.9218533",
  isbn="978-1-4503-6725-7",
  url="https://arxiv.org/abs/2004.10502"
}