Cannot get OpenCV3.0 cuda::calcHist() to return correct values

edit

Updated code paste. I was using cuda::normalize() instead of cv2::normalize() and feeding it GpuMat from cuda::calcHist() but the values returned from calcHist were b0rked. The calcHist() without CUDA works okay and so does multiple CUDA samples. Using OpenCV3.0rc1 with Cuda 7.0 on GTX470 and Ubuntu 14.04

void displayHist2(Mat b_hist, Mat g_hist, Mat r_hist){

int hist_w = 1024;
int hist_h = 800;
int bin_w = cvRound( (double) hist_w/256 );

Mat histImage(hist_h, hist_w, CV_8UC3, Scalar(0,0,0));
normalize(b_hist, b_hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());
normalize(g_hist, g_hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());
normalize(r_hist, r_hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());

Size s = b_hist.size();
int rows = s.height;
int cols = s.width;

if(rows == 0 && cols == 0 ) return;

for( int i = 1; i < 256 ; i++ ){
    line( histImage, Point( bin_w*(i-1), hist_h - cvRound(b_hist.at<float>(i-1)) ) ,
                     Point( bin_w*(i), hist_h - cvRound(b_hist.at<float>(i)) ),
                     Scalar( 255, 0, 0), 2, 8, 0  );
    line( histImage, Point( bin_w*(i-1), hist_h - cvRound(g_hist.at<float>(i-1)) ) ,
                     Point( bin_w*(i), hist_h - cvRound(g_hist.at<float>(i)) ),
                     Scalar( 0, 255, 0), 2, 8, 0  );
    line( histImage, Point( bin_w*(i-1), hist_h - cvRound(r_hist.at<float>(i-1)) ) ,
                     Point( bin_w*(i), hist_h - cvRound(r_hist.at<float>(i)) ),
                     Scalar( 0, 0, 255), 2, 8, 0  );
}

namedWindow("calcHist Demo", CV_WINDOW_AUTOSIZE );
imshow("calcHist Demo", histImage );
waitKey(0);

}

int main(int argc, char* argv[]){

Mat h_edges;
namedWindow("edges", 1);

Mat h_frame, h_dstframe, h_result;
Mat b_hist, g_hist, r_hist;

string filename = "default.mp4";
if(argc > 1 && argv[1] != string("")) filename = argv[1];

VideoCapture h_cap(filename);
if(!h_cap.isOpened()) return -1;

while(1){

    h_cap >> h_frame;
    if( !h_frame.data ) { return -1; }

    cvtColor(h_frame, h_frame, CV_BGR2Lab);
    imshow("edges", h_frame);

    cuda::GpuMat d_bdst, d_gdst, d_rdst, d_src;
    cuda::GpuMat d_matarr[3];

    d_src.upload(h_frame);
    cuda::split(d_src,d_matarr);

    cuda::calcHist(d_matarr[0], d_bdst);
    cuda::calcHist(d_matarr[1], d_gdst);
    cuda::calcHist(d_matarr[2], d_rdst);

    d_bdst.download(b_hist);
    d_gdst.download(g_hist);
    d_rdst.download(r_hist);

    displayHist2(b_hist, g_hist, r_hist);
}

}