Efficient Parallelization of H.264 Decoding with Macro-block Level Scheduling
Explore the innovative approach of parallelizing H.264 video decoding using macro-block level scheduling, enhancing efficiency and performance. Learn about dynamic task scheduling, frame-level encoding, and energy consumption evaluation in this insightful study.
Uploaded on | 0 Views
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
SVC parallelization on Android SVC parallelization on Android
ENERGY ENERGY- -EFFICIENT MULTI EFFICIENT MULTI- - THREADED VIDEO DECODING THREADED VIDEO DECODING
Introduction Parallelization Video sequence on different cores Decoding levels of group of pictures Independent slice within each frame Macro block level
Macro-block Level Applied for spatially predicted MBs No such restrictions for temporally predicted
Experiment Intel i7quad-core 1.6G, 6M cache WattsUp PRO power meter Use different video in these two experiment
Result Frame Level Encoding MVC mode Quantization parameter 22 30 fps Performance Evaluation Excluding the frame buffer storage time Energy Consumpton Subtracting the idel power from the average
Result Frame Level Encoding SVC encoder with base and enhancement layer Quantization parameter 46, 34 30 fps Open SVC decoder with MB decoding algorithm
EFFICIENT PARALLELIZATION OF EFFICIENT PARALLELIZATION OF H.264 DECODING WITH MACRO H.264 DECODING WITH MACRO BLOCK LEVEL BLOCK LEVEL SCHEDULING SCHEDULING IEEE International Conference on Multimedia and Expo, 2007
Introduction Macro-block parallelize Dynamically scheduling task at runtime
Introduction I - MB : difficult to parallelize Tight data dependency P - MB : easily parallelize No strong data dependency
Technique Three stage Preparse Highly sequential Render Significant opportunities for parallelism Filter Obviously parallel
Technique Prepare stage Buffer a small amount of recently decoded prediction modes/MVs from neighboring MGs
Schedule Greedy Static compile time Assume equal execution time for all MBs for each MB types Run time MB level MB types Encoded stream sizes
Experiment Resolution : 320x144 Contains I, P frames PentiumM 1.5GHz
Parallelization of H.264 video Parallelization of H.264 video decoder for embedded multicore decoder for embedded multicore processor processor IEEE International Conference on Multimedia and Expo, 2008
Introduction Balance load Data preloading
