HOG descriptors for blocks only

I am trying to calculate HOG features for block only. I explored hog.cpp listed under

opencv/module/gpu/src/

Below is the code that I am trying to change to compute the descriptors for blocks only.

void cv::gpu::HOGDescriptor::getDescriptors(const GpuMat& img, Size win_stride, GpuMat& descriptors, int descr_format)
{
    CV_Assert(win_stride.width % block_stride.width == 0 && win_stride.height % block_stride.height == 0);

    computeBlockHistograms(img);
    // give block back

/*
    const size_t block_hist_size = getBlockHistogramSize();
    Size blocks_per_win = numPartsWithin(win_size, block_size, block_stride);
    Size wins_per_img   = numPartsWithin(img.size(), win_size, win_stride);

    descriptors.create(wins_per_img.area(), static_cast<int>(blocks_per_win.area() * block_hist_size), CV_32F); */

    switch (descr_format)
    {
    case DESCR_FORMAT_ROW_BY_ROW:
        hog::extract_descrs_by_rows(win_size.height, win_size.width, block_stride.height, block_stride.width,
                                    win_stride.height, win_stride.width, img.rows, img.cols, block_hists.ptr<float>(), descriptors);
        break;
    case DESCR_FORMAT_COL_BY_COL:
        hog::extract_descrs_by_cols(win_size.height, win_size.width, block_stride.height, block_stride.width,
                                    win_stride.height, win_stride.width, img.rows, img.cols, block_hists.ptr<float>(), descriptors);
        break;
    default:
        CV_Error(CV_StsBadArg, "Unknown descriptor format");
    }
}

Here is the computeBlockHistograms function as well.

void cv::gpu::HOGDescriptor::computeBlockHistograms(const GpuMat& img)
{
    computeGradient(img, grad, qangle);

    size_t block_hist_size = getBlockHistogramSize();
    Size blocks_per_img = numPartsWithin(img.size(), block_size, block_stride);

    //   block_hists.create(1, block_hist_size * blocks_per_img.area(), CV_32F);
    block_hists = getBuffer(1, static_cast<int>(block_hist_size * blocks_per_img.area()), CV_32F, block_hists_buf);

    hog::compute_hists(nbins, block_stride.width, block_stride.height, img.rows, img.cols,
                        grad, qangle, (float)getWinSigma(), block_hists.ptr<float>());

    hog::normalize_hists(nbins, block_stride.width, block_stride.height, img.rows, img.cols,
                         block_hists.ptr<float>(), (float)threshold_L2hys);
}

It also utilizes hog.cu file opencv/module/gpu/src/cuda/ as well. I am relatively new to CUDA. Can someone help me to get the HOG features for block only on GPU.