为什么Opencv GPU代码比CPU慢

我正在笔记本上使用opencv242+VS2010
我试着在OpenCV中对GPU块进行一些简单的测试，但它显示GPU比CPU代码慢100倍。在这段代码中，我只是将彩色图像转换为灰度图像，使用cvtColor的功能

这是我的代码，PART1是CPU代码（测试CPU RGB2GRAY），PART2是上传图像到GPU，PART3是GPU RGB2GRAY，PART4又是CPU RGB2GRAY。有三件事让我很好奇：

1在我的代码中，part1是0.3ms，而part4（与part1完全相同）是40ms
2将图像上传到GPU的第二部分是6000ms
3第3部分（GPU代码）是11ms，对于这个简单的图像来说太慢了！

    #include "StdAfx.h"
    #include <iostream>
    #include "opencv2/opencv.hpp"
    #include "opencv2/gpu/gpu.hpp"
    #include "opencv2/gpu/gpumat.hpp"
    #include "opencv2/core/core.hpp"
    #include "opencv2/highgui/highgui.hpp"
    #include <cuda.h>
    #include <cuda_runtime_api.h>
    #include <ctime>
    #include <windows.h>
    using namespace std;
    using namespace cv;
    using namespace cv::gpu;
    int main()
    {
        LARGE_INTEGER freq;
        LONGLONG QPart1,QPart6;
        double dfMinus, dfFreq, dfTim;
        QueryPerformanceFrequency(&freq);
        dfFreq = (double)freq.QuadPart;
        cout<<getCudaEnabledDeviceCount()<<endl;
        Mat img_src = imread("d:\CUDA\train.png", 1);
        // PART1 CPU code~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
        // From color image to grayscale image.
        QueryPerformanceCounter(&freq);
        QPart1 = freq.QuadPart;
        Mat img_gray;
        cvtColor(img_src,img_gray,CV_BGR2GRAY);
        QueryPerformanceCounter(&freq);
        QPart6 = freq.QuadPart;
        dfMinus = (double)(QPart6 - QPart1);
        dfTim = 1000 * dfMinus / dfFreq;
        printf("CPU RGB2GRAY running time is %.2f msnn",dfTim);
        // PART2 GPU upload image~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
        GpuMat gimg_src;
        QueryPerformanceCounter(&freq);
        QPart1 = freq.QuadPart;
        gimg_src.upload(img_src);
        QueryPerformanceCounter(&freq);
        QPart6 = freq.QuadPart;
        dfMinus = (double)(QPart6 - QPart1);
        dfTim = 1000 * dfMinus / dfFreq;
        printf("Read image running time is %.2f msnn",dfTim);
        GpuMat dst1;
        QueryPerformanceCounter(&freq);
        QPart1 = freq.QuadPart;
        /*dst.upload(src_host);*/
        dst1.upload(imread("d:\CUDA\train.png", 1));
        QueryPerformanceCounter(&freq);
        QPart6 = freq.QuadPart;
        dfMinus = (double)(QPart6 - QPart1);
        dfTim = 1000 * dfMinus / dfFreq;
        printf("Read image running time 2 is %.2f msnn",dfTim);
        // PART3~ GPU code~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
        // gpuimage From color image to grayscale image.
        QueryPerformanceCounter(&freq);
        QPart1 = freq.QuadPart;
        GpuMat gimg_gray;
        gpu::cvtColor(gimg_src,gimg_gray,CV_BGR2GRAY);
        QueryPerformanceCounter(&freq);
        QPart6 = freq.QuadPart;
        dfMinus = (double)(QPart6 - QPart1);
        dfTim = 1000 * dfMinus / dfFreq;
        printf("GPU RGB2GRAY running time is %.2f msnn",dfTim);
        // PART4~CPU code(again)~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
        // gpuimage From color image to grayscale image.
        QueryPerformanceCounter(&freq);
        QPart1 = freq.QuadPart;
        Mat img_gray2;
        cvtColor(img_src,img_gray2,CV_BGR2GRAY);
        BOOL i_test=QueryPerformanceCounter(&freq);
        printf("%d n",i_test);
        QPart6 = freq.QuadPart;
        dfMinus = (double)(QPart6 - QPart1);
        dfTim = 1000 * dfMinus / dfFreq;
        printf("CPU RGB2GRAY running time is %.2f msnn",dfTim);
        cvWaitKey();
        getchar();
        return 0;
    }