// place the containing folder in your
//  libjacket/examples/ directory
//
// Chris McClanahan - 2011

#include <iostream>
#include <fstream>
#include <stdio.h>
#include <math.h>
#include <jacket.h>
#include <jacket_gfx.h>
#include <cv.h>
#include <cxcore.h>
#include <highgui.h>
#include "opencv2/gpu/gpu.hpp"



using namespace jkt;
using namespace std;
using namespace cv;
using namespace gpu;


const int ksz = 32;
Mat ker;

void gen(Mat& mat, int rows, int cols, int type, Scalar low, Scalar high) {
    mat.create(rows, cols, type);
    RNG rng(0);
    rng.fill(mat, RNG::UNIFORM, low, high);
}

int main() {
    ginfo();

    Mat src, dst;
    GpuMat d_src, d_dst, d_ker;
    gen(ker, ksz, ksz, CV_32F, -1, 1);
    int runs = 100;

    for (int size = 512; size < 4000; size += 512) {
        cout  << "size: " << size << "x" << size << endl;
        gen(src, size, size, CV_32FC1, 0, 1);

        try {
            // OpenCV
            {
                dst.create(size, size, CV_32FC1);
                d_src = src;
                d_dst.create(size, size, CV_32FC1);
                d_ker = ker;

                ConvolveBuf buf;
                convolve(d_src, d_ker, d_dst, false, buf); // Warm up
                int64 t = getTickCount();
                for (int i = 0; i < runs; ++i)
                    convolve(d_src, d_ker, d_dst, false, buf);
                cout << "  cv-gpu: " << (getTickCount() - t) / getTickFrequency() / (float)runs << endl;
            }

            // LibJacket
            {
                // extract cv image
                Mat jimg;
                src.convertTo(jimg, CV_32FC1);
                float* fgray = (float*)jimg.data;
                f32 I1 = f32(fgray, jimg.rows, jimg.cols);
                unsigned dimsb[] = {ksz, ksz};

                // gpu
                f32 jker = f32((float*)ker.data, ker.rows, ker.cols);
                f32 jdst = conv2(I1, jker, jktConvValid);
                gsync();
                int64 t = getTickCount();
                for (int i = 0; i < runs; ++i) {
                    jdst = conv2(I1, jker, jktConvValid);
                    gsync();
                }
                cout << "  jacket: " << (getTickCount() - t) / getTickFrequency() / (float)runs << endl;
            }

        } catch (gexception& e) {
            cout << e.what() << endl;
        }
    }

    return 0;
}

/*
Results for ksz = 32
====================
Libjacket v1.0.1 (build dd66add) by AccelerEyes
CUDA Driver: 270.81
CUDA Toolkit: v4.0

CUDA capable devices detected:
GPU0 Tesla C2050 / C2070, 2652 MB, Compute 2.0 (single,double) (in use)
size: 512x512
  cv-gpu: 0.00202607
  jacket: 0.00790995
size: 1024x1024
  cv-gpu: 0.00767946
  jacket: 0.0321756
size: 1536x1536
  cv-gpu: 0.00893694
  jacket: 0.0735304
size: 2048x2048
  cv-gpu: 0.0171747
  jacket: 0.131005
size: 2560x2560
  cv-gpu: 0.0177356
  jacket: 0.205862
size: 3072x3072
  cv-gpu: 0.0278928
  jacket: 0.297097
size: 3584x3584
  cv-gpu: 0.0268914
  jacket: 0.404806

Results for ksz = 64
====================
Libjacket v1.0.1 (build dd66add) by AccelerEyes
CUDA Driver: 270.81
CUDA Toolkit: v4.0

CUDA capable devices detected:
GPU0 Tesla C2050 / C2070, 2652 MB, Compute 2.0 (single,double) (in use)
size: 512x512
  cv-gpu: 0.0021476
  jacket: 0.00167873
size: 1024x1024
  cv-gpu: 0.00802897
  jacket: 0.00602738
size: 1536x1536
  cv-gpu: 0.00899348
  jacket: 0.00626257
size: 2048x2048
  cv-gpu: 0.0173659
  jacket: 0.0232162
size: 2560x2560
  cv-gpu: 0.0177426
  jacket: 0.0236838
size: 3072x3072
  cv-gpu: 0.0264366
  jacket: 0.0242362
size: 3584x3584
  cv-gpu: 0.0270701
  jacket: 0.0249083
*/