reference https://devblogs.nvidia.com/parallelforall/even-easier-introduction-cuda/
__global__ void add(int n, float *x, float *y) { int index = threadIdx.x; int stride = blockDim.x; for (int i = index; i < n; i += stride) y[i] = x[i] + y[i]; } int blockSize = 256; int numBlocks = (N + blockSize - 1) / blockSize; add<<<numBlocks, blockSize>>>(N, x, y); __global__ void add(int n, float *x, float *y) { int index = blockIdx.x * blockDim.x + threadIdx.x; int stride = blockDim.x * gridDim.x; for (int i = index; i < n; i += stride) y[i] = x[i] + y[i]; } #include <iostream> #include <math.h> // function to add the elements of two arrays void add(int n, float *x, float *y) { for (int i = 0; i < n; i++) y[i] = x[i] + y[i]; } int main(void) { int N = 1<<20; // 1M elements float *x = new float[N]; float *y = new float[N]; // initialize x and y arrays on the host for (int i = 0; i < N; i++) { x[i] = 1.0f; y[i] = 2.0f; } // Run kernel on 1M elements on the CPU add(N, x, y); // Check for errors (all values should be 3.0f) float maxError = 0.0f; for (int i = 0; i < N; i++) maxError = fmax(maxError, fabs(y[i]-3.0f)); std::cout << "Max error: " << maxError << std::endl; // Free memory delete [] x; delete [] y; return 0; }