Moving Data

cudaMalloc(&d_data, size);
cudaMemcpy(d_data, h_data, size, cudaMemcpyHostToDevice);
kernel<<<blocks, threads>>>(d_data);
kernel2<<<blocks, threads>>>(d_data);

cudaMalloc(&d_data, size);
cudaMemcpy(d_data, h_data, size, cudaMemcpyHostToDevice);
kernel<<<blocks, threads>>>(d_data);
cudaMemcpy(h_data, d_data, size, cudaMemcpyDeviceToHost);
cudaMemcpy(d_data, h_data, size, cudaMemcpyHostToDevice);
kernel2<<<blocks, threads>>>(d_data);