相关疑难解决方法(0)

我正在测试新的CUDA 8以及Pascal Titan X GPU,并期待我的代码加速,但由于某种原因它最终会变慢.我在Ubuntu 16.04上.

以下是可以重现结果的最小代码:

CUDASample.cuh

class CUDASample{
 public:
  void AddOneToVector(std::vector<int> &in);
};

CUDASample.cu

__global__ static void CUDAKernelAddOneToVector(int *data)
{
  const int x  = blockIdx.x * blockDim.x + threadIdx.x;
  const int y  = blockIdx.y * blockDim.y + threadIdx.y;
  const int mx = gridDim.x * blockDim.x;

  data[y * mx + x] = data[y * mx + x] + 1.0f;
}

void CUDASample::AddOneToVector(std::vector<int> &in){
  int *data;
  cudaMallocManaged(reinterpret_cast<void **>(&data),
                    in.size() * sizeof(int),
                    cudaMemAttachGlobal);

  for (std::size_t i = 0; i < in.size(); …