Nvcc 的版本与 CUDA 不同

什么是Nvcc和CUDA?

c++
#include 
__global__ void vectorAdd(int *a, int *b, int *c, int n) {
    int i = threadIdx.x;
    if (i < n) {
        c[i] = a[i] + b[i];
    }
}
int main() {
    int n = 100;
    int a[n], b[n], c[n];
    int *dev_a, *dev_b, *dev_c;
    cudaMalloc((void**)&dev_a, n * sizeof(int));
    cudaMalloc((void**)&dev_b, n * sizeof(int));
    cudaMalloc((void**)&dev_c, n * sizeof(int));
    for (int i = 0; i < n; i++) {
        a[i] = i;
        b[i] = i;
    }
    cudaMemcpy(dev_a, a, n * sizeof(int), cudaMemcpyHostToDevice);
    cudaMemcpy(dev_b, b, n * sizeof(int), cudaMemcpyHostToDevice);
    vectorAdd<<<1, n>>>(dev_a, dev_b, dev_c, n);
    cudaMemcpy(c, dev_c, n * sizeof(int), cudaMemcpyDeviceToHost);
    for (int i = 0; i < n; i++) {
        printf("%d + %d = %d\n", a[i], b[i], c[i]);
    }
    cudaFree(dev_a);
    cudaFree(dev_b);
    cudaFree(dev_c);
    return 0;
}