Пытаясь ускорить простой алгоритм с использованием графического процессора с OpenCV, я заметил, что на моей машине (Ubuntu 12.10, NVidia 9800GT, Cuda 4.2.9, g ++ 4.7.2) версия графического процессора на самом деле медленнее, чем версия процессора. Я проверил с помощью следующего кода.

#include 
#include 

#include 
#include 

int main()
{
    using namespace cv;
    using namespace std;

    Mat img1(512, 512, CV_32FC3, Scalar(0.1f, 0.2f, 0.3f));
    Mat img2(128, 128, CV_32FC3, Scalar(0.2f, 0.3f, 0.4f));
    Mat img3(128, 128, CV_32FC3, Scalar(0.3f, 0.4f, 0.5f));

    auto startCPU = chrono::high_resolution_clock::now();
    double resultCPU(0.0);
    cout < "CPU ... " < flush;
    for (int y(0); y < img2.rows; ++y)
    {
        for (int x(0); x < img2.cols; ++x)
        {
            Mat roi(img1(Rect(x, y, img2.cols, img2.rows)));
            Mat diff;
            absdiff(roi, img2, diff);
            Mat diffMult(diff.mul(img3));
            Scalar diffSum(sum(diff));
            double diffVal(diffSum[0] + diffSum[1] + diffSum[2]);
            resultCPU += diffVal;
        }
    }
    auto endCPU = chrono::high_resolution_clock::now();
    auto elapsedCPU = endCPU - startCPU;
    cout < "done. " < resultCPU < " - ticks: " < elapsedCPU.count() < endl;

    gpu::GpuMat img1GPU(img1);
    gpu::GpuMat img2GPU(img2);
    gpu::GpuMat img3GPU(img3);
    gpu::GpuMat diffGPU;
    gpu::GpuMat diffMultGPU;
    gpu::GpuMat sumBuf;

    double resultGPU(0.0);
    auto startGPU = chrono::high_resolution_clock::now();
    cout < "GPU ... " < flush;
    for (int y(0); y < img2GPU.rows; ++y)
    {
        for (int x(0); x < img2GPU.cols; ++x)
        {
            gpu::GpuMat roiGPU(img1GPU, Rect(x, y, img2GPU.cols, img2GPU.rows));
            gpu::absdiff(roiGPU, img2GPU, diffGPU);
            gpu::multiply(diffGPU, img3GPU, diffMultGPU);
            Scalar diffSum(gpu::sum(diffMultGPU, sumBuf));
            double diffVal(diffSum[0] + diffSum[1] + diffSum[2]);
            resultGPU += diffVal;
        }
    }
    auto endGPU = chrono::high_resolution_clock::now();
    auto elapsedGPU = endGPU - startGPU;
    cout < "done. " < resultGPU < " - ticks: " < elapsedGPU.count() < endl;
}