High-Level Synthesis Implementation of SAD for VVC Standard
The Versatile Video Coding (H.266/VVC) standard is the latest generation codec developed by the Joint Video Experts Team (JVET). The VVC standard improves the encoding performance compared to previous standards at the cost of an increase in computational complexity. Therefore, researchers focus on r...
Saved in:
Published in | 2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP) Vol. 1; pp. 83 - 86 |
---|---|
Main Authors | , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
11.07.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The Versatile Video Coding (H.266/VVC) standard is the latest generation codec developed by the Joint Video Experts Team (JVET). The VVC standard improves the encoding performance compared to previous standards at the cost of an increase in computational complexity. Therefore, researchers focus on reducing coding complexity through hardware acceleration. This paper introduces an efficient High-Level Synthesis (HLS) hardware design of the Sum of Absolute Difference (SAD) for the VVC encoder. In fact, different directives are initially employed to the SAD C code to generate an optimized hardware IP (Intellectual property) design, using Xilinx Vivado HLS platform. Then, using the Xilinx Vivado tool, this IP is implemented on the ZYNQ-7 ZC702 Evaluation Board. The synthesis report shows that the SW/HW design system requires power consumption of \mathbf{1. 7 3 6} \mathrm{W}, \mathbf{2 0 \%} of Look-up Tables (LUTs), \mathbf{4 \%} of RAM blocks and 6 \% of FlipFlops (FFs). |
---|---|
ISSN: | 2687-878X |
DOI: | 10.1109/ATSIP62566.2024.10638861 |