Parallel Volume Rendering Algorithms for Computa- tional Flow Imaging

Abstract: Computational flow imaging (CFI) uses theoretical predictions of the interaction and transmission of optical waves through theoretical flowfield to generate digital pictures that simu-late real observations, but visualizing three-dimensional unstructured data from aerodynamics calculations is challenging because the associated meshes are typically large in size and irregular in both shape and resolution. The goal of this research is to develop a fast, efficient parallel vol-ume rendering algorithm of computational flow imaging (corresponding to shadowgraph, schlieren and interferometric) for parallel distributed-memory supercomputers consisting of a large number of powerful processors. We use a preprocessing procedure that the whole flow field is divided into new regular regions in which the voxels are distributed by x and y coordinates so that the ray-casting and field reconstructing can provide maximum flexibility in the data distribu-tion and rendering steps