UHD 8K energy-quality scalable HEVC intra-prediction SAD unit hardware using optimized and configurable imprecise adders
- PDF / 1,649,093 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 77 Downloads / 157 Views
ORIGINAL RESEARCH PAPER
UHD 8K energy‑quality scalable HEVC intra‑prediction SAD unit hardware using optimized and configurable imprecise adders Roger Porto1,2 · Marcel Correa1,2 · Jones Goebel1 · Bruno Zatt1 · Nuno Roma3,4 · Luciano Agostini1 · Marcelo Porto1 Received: 30 April 2019 / Accepted: 28 November 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract Real-time digital video coding became a mandatory feature in current consumer electronic devices due to the popularization of video applications. However, efficiently encoding videos is an extremely processing/energy-demanding task, especially at high resolutions and frame rates. Thus, the limited energy resources and the dynamically varying system status (such as workload, battery level, user settings, etc.) require energy-efficient solutions capable to support run-time energy-quality scalability. In this work, we present an energy-quality scalable SAD Unit hardware architecture for the HEVC intra-frame prediction targeting real-time processing of UHD 8K (7680 × 4320) videos at 60 frames per second. Approximate computing is used to provide energy-quality scalability by employing configurable imprecise operators. The proposed Energy-Quality scalable architecture supports four operation points: precise computing, and 3-bit, 5-bit or 7-bit imprecision. When implemented in a 45-nm technology using Nangate standard cells library and running at 269 MHz, the proposed architecture consumes from 8.42 to 7.38 mJ to process each UHD 8K frame, according to the selected imprecision level. As a drawback, the coding efficiency (measured in BD rate) is reduced from 0.28 to 1.72%. Compared to the related works, this is the only intra-frame prediction SAD unit able to provide energy-quality scalability. Keywords Energy-quality scalability · Video coding · Intra-prediction · SAD · Scalable hardware design · Approximate computing
1 Introduction The omnipresence of digital videos and the increasing demand for higher resolutions (Full HD, UHD 4K, and UHD 8K), higher frame rates (60 fps, 120 fps, etc.), better color representations (HDR—high dynamic range), and immersive experience (3D and omnidirectional videos) drastically increased the amount of video content to be processed, stored, and transmitted. As a result, video traffic over the internet consumed more than 56 exabytes per month in 2017, * Roger Porto [email protected] 1
Video Technology Research Group, Group of Architectures and Integrated Circuits, Federal University of Pelotas (UFPel), Pelotas, RS 96010‑900, Brazil
2
Sul-Rio-Grandense Federal Institute of Science and Technology (IFSul), Bagé, Brazil
3
Instituto Superior Técnico (IST), Universidade de Lisboa, Lisbon, Portugal
4
INESC-ID, Lisbon, Portugal
using 75% of the global internet traffic [1]. In this trend, it is expected that video contents will consume 240 exabytes per month by 2022, or 82% of the total internet traffic [1]. Consequently, the pressure between the fast-increasing traffic and the limited network
Data Loading...
