Implementation of Motion Estimation Based On Heterogeneous Parallel Computing System with OpenCL

Heterogeneous computing system increases the performance of parallel computing in many domain of general purpose computing with CPU, GPU and other accelerators. Open Computing Language (OpenCL) is the first open, royalty-free standard for heterogenous computing on multi hardware platforms. In this paper, we propose a parallel Motion Estimation (ME) algorithm implemented using OpenCL and present several optimization strategies applied in our OpenCL implementation of the motion estimation. In the same time, we implement the proposed algorithm on our heterogeneous computing system which contains one CPU and one GPU, and propose one method to determine the balance to distribute the workload in heterogeneous computing system with OpenCL. According to experiments, our motion estimator with achieves 100x to 150x speed-up compared with its implementation with C code executed by single CPU core and our proposed method obtains obviously enhancement of performance in based on our heterogeneous computing system.