I am using dpc++ compiler integrated with microsoft visual studio, I wrote a small app to apply a filter to an image (gray scale), the app will compute the new value of the pixel on the device and store it on new filtered_image_buffer, while computing, the value is float and then it will be converted to uchar but the behavior is different when I use cpu vs gpu selector, on gpu the filter is applied correctly and the result image is fine, but in cpu the image is in chaos.
cpu that I am using: Intel(R) Core(TM) i7-8665U
gpu: Intel(R) UHD Graphics 620
here the results for gpu vs cpu (filter to sharpen the image is used)
code:
```
#include <sycl/sycl.hpp>
#include <iostream>
#include <opencv2/opencv.hpp>
using namespace sycl;
int main(int argc, char* argv[]) {
cv::Mat image = cv::imread("oneapi1.png", cv::IMREAD_GRAYSCALE);
if (image.empty()) {
std::cout << "Could not open or find the image" << std::endl;
return -1;
}
std::vector<uchar> imageData;
imageData.assign(image.data, image.data + image.total());
buffer <uchar, 1> imageBuffer(imageData.data(), range<1>(image.total()));
cv::Mat filteredImage = image.clone();
std::vector<uchar> filteredImageData;
filteredImageData.assign(filteredImage.data, filteredImage.data + filteredImage.total() * filteredImage.channels());
cpu_selector selector;
queue q{ selector };
auto height = image.rows;
auto width = image.cols;
const int filterHeight = 5;
const int filterWidth = 5;
float filter[filterHeight][filterWidth] = {
{-1, -1, -1, -1, -1,},
{-1, 1.5, 1.5, 1.5, -1},
{-1, 1.5, 5, 1.5, -1},
{-1, 1.5, 1.5, 1.5, -1},
{-1, -1, -1, -1, -1}
};
buffer <float, 2> filterBuf(range<2>(filterHeight, filterWidth));
{
auto filterBufAcc = filterBuf.get_access<access::mode::read_write>();
for (int i = 0; i < filterHeight; i++) {
for (int j = 0; j < filterWidth; j++) {
filterBufAcc[i][j] = filter[i][j];
}
}
}
{
buffer <uchar, 1> filteredImageBuffer(filteredImageData.data(), range<1>(filteredImage.total() * filteredImage.channels()));
q.submit([&](handler& h) {
auto imageAcc = imageBuffer.get_access<access::mode::read>(h);
auto filteredImageAcc = filteredImageBuffer.get_access<>(h);
auto filterAcc = filterBuf.get_access<access::mode::read>(h);
h.parallel_for(range<2>{height - ((filterHeight / 2) * 2), width - ((filterWidth / 2) * 2)}, [=](item<2> id) {
float value = 0;
auto global_row = id.get_id(0) + (filterHeight / 2);
auto global_column = id.get_id(1) + (filterWidth / 2);
//filter need a special case for edges, but here it just skip them
for (int i = 0; i < filterHeight; i++) {
for (int j = 0; j < filterWidth; j++) {
value += filterAcc[i][j] * imageAcc[(id.get_id(0) + i) * width + id.get_id(1) + j];
}
}
filteredImageAcc[global_row * width + global_column] = (uchar)(value);
});
});
q.wait();
}
cv::Mat filteredImageResult(height, width, CV_8UC1, filteredImageData.data());
cv::namedWindow("filtered Image", cv::WINDOW_NORMAL);
cv::imshow("filtered Image", filteredImageResult);
cv::namedWindow("original Image", cv::WINDOW_NORMAL);
cv::imshow("original Image", image);
cv::waitKey(0);
return 0;
}
```
the original image is attached
Link Copied
