问为什么Nvidia profiler不显示统一内存信息

EN

// CUDA kernel to add elements of two arrays
__global__
void add(int n, float *x, float *y)
{
int index = blockIdx.x * blockDim.x + threadIdx.x;
int stride = blockDim.x * gridDim.x;
for (int i = index; i < n; i += stride)
    y[i] = x[i] + y[i];
}

int main(void)
{
int N = 1 << 20;
float *x, *y;

// Allocate Unified Memory -- accessible from CPU or GPU
cudaMallocManaged(&x, N * sizeof(float));
cudaMallocManaged(&y, N * sizeof(float));

// initialize x and y arrays on the host
for (int i = 0; i < N; i++) {
    x[i] = 1.0f;
    y[i] = 2.0f;
}

// Launch kernel on 1M elements on the GPU
int blockSize = 256;
int numBlocks = (N + blockSize - 1) / blockSize;
add <<< numBlocks, blockSize >>>(N, x, y);

// Wait for GPU to finish before accessing on host
cudaDeviceSynchronize();

// Check for errors (all values should be 3.0f)
float maxError = 0.0f;
for (int i = 0; i < N; i++)
    maxError = fmax(maxError, fabs(y[i] - 3.0f));
std::cout << "Max error: " << maxError << std::endl;

// Free memory
cudaFree(x);
cudaFree(y);

return 0;
}

"==852== Warning: Unified Memory Profiling is not supported on the
current configuration because a pair of devices without peer-to-peer
support is detected on this multi-GPU setup. When peer mappings are
not available, system falls back to using zero-copy memory. It can
cause kernels, which access unified memory, to run slower. More
details can be found at:
http://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#um-
managed-memory"