int *h_data, *d_data;
cudaMalloc((void **)&d_data, DSIZE*sizeof(int));
h_data = (int *)malloc(DSIZE*sizeof(int));
// fill up h_data[] with data
cudaMemcpy(d_data, h_data, DSIZE*sizeof(int), cudaMemcpyHostToDevice);
for (int i = 0; i < 60000; i++)
my_kernel<<<grid_dim, block_dim>>>(d_data)
cudaMemcpy(h_data, d_data, DSIZE*sizeof(int), cudaMemcpyDeviceToHost);
...
1 回答
是的,你可以完全按照你的描述做到: