http://graphics.stanford.edu/courses/cs348v-18-winter/lectures/08_dnneval.pdf

conv_basic.cpp

// image convolution (3x3 conv)
int WIDTH = 1024;
int HEIGHT = 1024;
float input[(WIDTH + 2) * (HEIGHT + 2)];
float output[WIDTH * HEIGHT];
float weights[] = {1.0 / 9, 1.0 / 9, 1.0 / 9,
                   1.0 / 9, 1.0 / 9, 1.0 / 9,
                   1.0 / 9, 1.0 / 9, 1.0 / 9};

for (int j = 0; j < HEIGHT; j++)
{
    for (int i = 0; i < WIDTH; i++)
    {
        float tmp = 0.f;
        for (int jj = 0; jj < 3; jj++)
            for (int ii = 0; ii < 3; ii++)
                tmp += input[(j + jj) * (WIDTH + 2) + (i + ii)] * weights[jj * 3 + ii];

        output[j * WIDTH + i] = tmp;
    }
}

conv_stride.cpp

int WIDTH = 1024;
int HEIGHT = 1024;
int STRIDE = 2;
float input[(WIDTH + 2) * (HEIGHT + 2)];
float output[(WIDTH / STRIDE) * (HEIGHT / STRIDE)];
float weights[] = {1.0 / 9, 1.0 / 9, 1.0 / 9,
                   1.0 / 9, 1.0 / 9, 1.0 / 9,
                   1.0 / 9, 1.0 / 9, 1.0 / 9};

for (int j = 0; j < HEIGHT; j += STRIDE)
{
    for (int i = 0; i < WIDTH; i += STRIDE)
    {
        float tmp = 0.f;
        for (int jj = 0; jj < 3; jj++)
            for (int ii = 0; ii < 3; ii++)
                tmp += input[(j + jj) * (WIDTH + 2) + (i + ii)] * weights[jj * 3 + ii];

        output[(j / STRIDE) * (WIDTH / STRIDE) + (i / STRIDE)] = tmp;
    }
}