Fractal image generation algorithms exhibit extreme parallelizability. Using general purpose graphics processing unit (GPU) programming to implement escape-time algorithms for Julia sets of functions,parallel methods generate visually attractive fractal images much faster than traditional methods. Vastly improved speeds are achieved using this method of computation, which allow real-time generation and display of images. A comparison is made between sequential and parallel implementations of the algorithm. An application created by the authors demonstrates using the increased speed to create dynamic imaging of fractals where the user may explore paths of parameter values corresponding to a given functions Mandelbrot set. Examples are given of artistic and mathematical insights gained by experiencing fractals interactively and from the ability to sample the parameter space quickly and comprehensively.
Download