Hybrid Multi-Core Algorithms for Regular Image Filtering Applications

GPGPU has received lot of attention in the past few years mainly because of the performance gain GPUs offer at a low price. Recently, researchers have identified hybrid multi-core computing as a better solution compared to accelerator based computing for several problems. In this paper, we evaluate two regular problems in image processing, bilateral filtering and convolution, on a hybrid multi-core platform. We provide a detailed analysis of these algorithms by comparing their performance on three platforms 1)CPU+GPU hybrid, 2) pure GPU and 3)pure CPU. We show that clear performance gains can be obtained simply by using basic techniques like data decomposition and overlapped execution, when a hybrid computing model is used. Finally, we conclude by discussing some future prospects in the area of hybrid computing.