#include <iostream>
__global__ void add(int a, int b, int* c)
{
*c = a + b;
}
int main(void)
{
int c;
int* dev_c;
cudaError_t(cudaMalloc((void**)& dev_c, sizeof(int)));
add << <1, 1 >> > (2, 7, dev_c);
cudaError_t(cudaMemcpy(&c,
dev_c,
sizeof(int),
cudaMemcpyDeviceToHost));
printf("2 + 7 = %d\n", c);
cudaFree(dev_c);
return 0;
}
GPU高性能编程_CUDA实战_page18
最新推荐文章于 2022-12-14 12:11:04 发布