欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

CUDA C++第一个项目“Hello World”

程序员文章站 2022-05-08 13:36:11
...
#include <iostream>
#include <cmath>

// Kernel function to add the elements of two arrays
__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];
}

int main() {
    int N = 1 << 20;
    float *x, *y;

    // Allocate Unified Memory – accessible from CPU or GPU
    cudaMallocManaged(&x, N * sizeof(float));
    cudaMallocManaged(&y, N * sizeof(float));
    // 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 GPU
    add<<<1, 1>>>(N, x, y);
    // Wait for GPU to finish before accessing on host
    cudaDeviceSynchronize();

    // 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
    cudaFree(x);
    cudaFree(y);
    return 0;
}