Embracing approximate computing for energy-efficient motion estimation in high efficiency video coding

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in KonferenzbandBeigetragenBegutachtung

Beitragende

Abstract

Approximate Computing is an emerging paradigm for developing highly energy-efficient computing systems. It leverages the inherent resilience of applications to trade output quality with energy efficiency. In this paper, we present a novel approximate architecture for energy-efficient motion estimation (ME) in high efficiency video coding (HEVC). We synthesized our designs for both ASIC and FPGA design flows. ModelSim gate-level simulations are used for functional and timing verification. We comprehensively analyze the impact of heterogeneous approximation modes on the power/energy-quality tradeoffs for various video sequences. To facilitate reproducible results for comparisons and further research and development, the RTL and behavioral models of approximate SAD architectures and constituting approximate modules are made available at https://sourceforge.net/projects/lpaclib/.

Details

OriginalspracheEnglisch
TitelDesign, Automation & Test in Europe Conference & Exhibition (DATE), 2017
ErscheinungsortLausanne
Herausgeber (Verlag)IEEE Xplore
Seiten1384-1389
Seitenumfang6
ISBN (elektronisch)978-3-9815370-8-6, 978-3-9815370-9-3
ISBN (Print)978-1-5090-5826-6
PublikationsstatusVeröffentlicht - 11 Mai 2017
Peer-Review-StatusJa

Publikationsreihe

ReiheDesign, Automation and Test in Europe Conference and Exhibition (DATE)
ISSN1530-1591

Konferenz

Titel20th Design, Automation and Test in Europe, DATE 2017
Dauer27 - 31 März 2017
StadtSwisstech, Lausanne
LandSchweiz

Schlagworte

Forschungsprofillinien der TU Dresden

Ziele für nachhaltige Entwicklung

Schlagwörter

  • Approximate computing, Energy efficiency, Hardware accelerator, HEVC, Motion estimation, Video coding

Bibliotheksschlagworte