GpuMatのcudaMallocPitchが遅くなる再現コード

gpumat_memory_performance.cpp

#include <opencv2/core.hpp>
#include <opencv2/core/cuda.hpp>
#include <cuda_runtime.h>
#include <device_launch_parameters.h>
#include <iostream>

int main(int argc, const char * argv[])
{
    cudaFree(0); // dummy call

    const size_t width   = 256;
    const size_t height  = 256;
    const size_t elemSize = 12;
    for (int i = 0; i < 5; i++)
    {
#if 1
        cv::cuda::GpuMat d_img(cv::Size(width, height), CV_32FC3); // cudaMallocPitch is slow(only first call)
#else
        size_t step = 0;
        unsigned char *data = NULL;
        cudaMallocPitch(&data, &step, elemSize * width, height);
        cudaFree(data);
#endif
    }

    return 0;
}

@keineahnung2345 Thank you for your information!