Parallel Processing of Sequential Media Algorithms on Heterogeneous Multi-Processor System-on-Chip

Abstract

Heterogeneous Multi-Processor System-on-Chip (MPSoC) and media processing are comprehensively applied in mobile electronic commerce. And heterogeneous MPSoCs provides more opportunities for parallelization accelerating of sequential media algorithms. However, the parallelization researches of heterogeneous MPSoC applications lags far behind the development of MPSoC hardware platform. Therefore, utilizing parallelization opportunity of MPSoC for improving performance and efficiency of media applications has been one of the hottest researches in the field of embedded system. This paper proposes a new approach that parallelizes sequential media algorithms on heterogeneous MPSoC using program transformation and application-to-architecture mapping techniques. Data locality and communication cost are optimized during the parallel processing. Moreover, the difference between processing elements, reflected in architecture templates, is used to achieve “the maximum” performance and efficiency of heterogeneous MPSoCs. Finally, an experiment shows the proposed approach can obtain approximate or better accelerating than the manual parallel processing by experienced designers.