Massively parallel isosurface extraction

Abstract

Experiences during the investigation of parallel methods for faster isosurface generation on SIMD (single instruction stream, multiple data stream) machines are described. A sequential version of a well-known isosurfacing algorithm is algorithmically enhanced for a particular type of SIMD architecture. The SIMD implementation takes full advantage of the data parallel nature of the algorithm, and experiments have proven the implementation to be highly scalable. A parallel tool, which can generate 170 K polygons/s, gives scientists the means to explore large 3D scalar or vector fields interactively.<>