Abstract
The H.264/AVC video coding standard features diverse computational hot spots that need to be accelerated to cope with the significantly increased complexity compared to previous standards. In this paper, we propose an optimized application structure (i.e. the arrangement of functional components of an application determining the data flow properties) for the H.264 encoder which is suitable for application-specific and reconfigurable hardware platforms. Our proposed application structural optimization for the computational reduction of the Motion Compensated Interpolation is independent of the actual hardware platform that is used for execution. For a MIPS processor we achieve an average speedup of approximately 60× for Motion Compensated Interpolation. Our proposed application structure reduces the overhead for Reconfigurable Platforms by distributing the actual hardware requirements amongst the functional blocks. This increases the amount of available reconfigurable hardware per Special Instruction (within a functional block) which leads to a 2.84× performance improvement of the complete encoder when compared to a Benchmark Application with standard optimizations. We evaluate our application structure by means of four different hardware platforms.
Original language | English (US) |
---|---|
Pages (from-to) | 183-210 |
Number of pages | 28 |
Journal | Journal of Signal Processing Systems |
Volume | 60 |
Issue number | 2 |
DOIs | |
State | Published - Aug 2010 |
Keywords
- ASIP
- H.264
- Hardware accelerators
- In-loop de-blocking filter
- Motion compensation
- Motion estimation
- MPEG-4 AVC
- Rate distortion
- Reconfigurable platform
- RISPP
- Special instructions
ASJC Scopus subject areas
- Control and Systems Engineering
- Theoretical Computer Science
- Signal Processing
- Information Systems
- Modeling and Simulation
- Hardware and Architecture