Key Sets Analysis of Compiler Vector Options for H.264 Video Compression Algorithms Implemented on the MIPS SIMD Architecture
Preprint
- 5 June 2023
- preprint
- Published by Springer Nature in Research Square
Abstract
The paper offers metrics to evaluate the image processing performance and video processing programs implemented on the MIPS SIMD Architecture (MSA). These metrics were also used to analyze and present key sets for the GCC compiler. As a result of the analysis, which was performed earlier, numerical representations of each parameter of four algorithms (CABAC, CAVLC, FDCT-IDCT, and Motion Estimation), used in the H.264 video compression standard, were calculated, and 5952 key sets were obtained, respectively. The weight coefficients were determined for each of the key parameters according to the Saati hierarchy analysis methodology. After that, using weight functions, 372 recommended sets of keys were determined, the target functions of which are maximal for each of the 4 algorithms considered.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Study of Vector Processor Architectures for Image Processing Using Model Profiling2019
- Using Ensemble Learning to Improve Automatic Vectorization of Tensor Contraction ProgramIEEE Access, 2018
- The weighted sum method for multi-objective optimization: new insightsStructural and Multidisciplinary Optimization, 2009
- The long and winding road to high-performance image processing with MMX/SSE2002
- Data optimization: Allocation of arrays to reduce communication on SIMD machinesJournal of Parallel and Distributed Computing, 1990