This package contains sample code for use in the GPU workshop. The code is described in more detail in the accompanying slides.

This sample queries the properties of the CUDA devices present in the system.

A simple example of a kernel to add two vectors elementwise

The example demonstrates several kernels that do simple math operations

This sample demonstrates the use of mapped variables.

This sample demonstrates the __device__ qualifier.

Compute blockwise sums of a vector x of length n.

Compute column sums of a M x N array. Each column is reduced by a single thread block.

Compute column sums of a M x N array. Each column is reduced by several thread blocks.

simpleArrayfire/simplearrayfire.cu

Utilities and macros