WOLFRAM

Wolfram Language & System Documentation Center

Speed Up Computations with Parallel GPU Computing

Write code that will use the maximum available precision on the specific CUDA or OpenCL device.

    
First, define the OpenCL code to build the Julia set fractal:
Wolfram Language code: code = " __kernel void julia_kernel(__global float *set, long width, long height, float cx, float cy) { long xIndex = get_global_id(0); long yIndex = get_global_id(1); long ii; float x = ZOOM_LEVEL*(width/2 - xIndex); float y = ZOOM_LEVEL*(height/2 - yIndex); float tmp; float c; if (xIndex < width && yIndex < height) { for (ii = 0; ii < MAX_ITERATIONS && x*x + y*y < BAILOUT; ii++) { tmp = x*x - y*y + cx; y = 2*x*y + cy; x = tmp; } c = log(0.1f + sqrt(x*x + y*y)); set[xIndex + yIndex*width] = c; } } ";
Compile and link the OpenCL code automatically in the Wolfram Language:
Wolfram Language code: Needs["OpenCLLink`"] {width, height} = {512, 512}; jset = OpenCLMemoryAllocate["Float", {height, width}]; JuliaCalculate = OpenCLFunctionLoad[code, "julia_kernel", {{"Float", _, "Output"}, _Integer, _Integer, "Float", "Float"}, {16, 16}, "Defines" -> {"MAX_ITERATIONS" -> 10, "ZOOM_LEVEL" -> "0.0050", "BAILOUT" -> "4.0"}];
Now you can build the interactive interface to dynamically call the OpenCL code:
Wolfram Language code: Manipulate[ JuliaCalculate[jset, width, height, c[[1]], c[[2]], {width, height}]; ReliefPlot[OpenCLMemoryGet[jset], DataRange -> {{-2.0, 2.0}, {-2.0, 2.0}}, ImageSize -> 256, ColorFunction -> "SunsetColors"], {{c, {0, 1}}, {-2, -2}, {2, 2}, Locator}]