Evaluation of parallel paradigms on Anisotropic Nonlinear Diffusion

Anisotropic Nonlinear Diffusion (AND) is a powerful noise reduction technique in the field of computer vision. This method is based on a Partial Differential Equation (PDE) tightly coupled with a massive set of eigensystems. Denoising large 3D images in biomedicine and structural cellular biology by AND is extremely expensive from a computational point of view, and the requirements may become so huge that parallel computing turns out to be essential. This work addresses the parallel implementation of AND. The parallelization is carried out by means of three paradigms: (1) Shared address space paradigm, (2) Message passing paradigm, and (3) Hybrid paradigm. The three parallel approaches have been evaluated on two parallel platforms: (1) a DSM (Distributed Shared Memory) platform based on cc-NUMA memory access and (2) a cluster of Symmetric biprocessors. An analysis of the performance of the three strategies has been accomplished to determine which is the most suitable paradigm for each platform.