cuda编程实例 linux

#include <iostream>
#include <cuda_runtime.h>

__global__ void vectorAdd(int *a, int *b, int *c, int n) {
    int i = blockIdx.x * blockDim.x + threadIdx.x;
    if (i < n) {
        c[i] = a[i] + b[i];
    }
}

int main() {
    int n = 10;
    int size = n * sizeof(int);

    int *h_a = (int*)malloc(size);
    int *h_b = (int*)malloc(size);
    int *h_c = (int*)malloc(size);

    for (int i = 0; i < n; ++i) {
        h_a[i] = i;
        h_b[i] = i * 2;
    }

    int *d_a, *d_b, *d_c;
    cudaMalloc((void**)&d_a, size);
    cudaMalloc((void**)&d_b, size);
    cudaMalloc((void**)&d_c, size);

    cudaMemcpy(d_a, h_a, size, cudaMemcpyHostToDevice);
    cudaMemcpy(d_b, h_b, size, cudaMemcpyHostToDevice);

    int threadsPerBlock = 256;
    int blocksPerGrid = (n + threadsPerBlock - 1) / threadsPerBlock;
    vectorAdd<<<blocksPerGrid, threadsPerBlock>>>(d_a, d_b, d_c, n);

    cudaMemcpy(h_c, d_c, size, cudaMemcpyDeviceToHost);

    for (int i = 0; i < n; ++i) {
        std::cout << h_a[i] << " + " << h_b[i] << " = " << h_c[i] << std::endl;
    }

    cudaFree(d_a);
    cudaFree(d_b);
    cudaFree(d_c);
    free(h_a);
    free(h_b);
    free(h_c);

    return 0;
}

nvcc vectorAdd.cu -o vectorAdd

./vectorAdd