#include <stdint.h>
#include <stdlib.h>

#define DCT_SIZE 8
#define TOTAL_DCT_BLOCKS 100

#define element_t int16_t
#define real_t double

#define DCT_COS_TABLE_SIZE 32
// DCT_COS_TABLE[i] = cos(i * PI / (2 * DCT_SIZE))
#define DCT_COS_TABLE (double[DCT_COS_TABLE_SIZE]) { \
    1, 0.980785, 0.92388, 0.83147, 0.707107, 0.55557, 0.382683, \
    0.19509, 0, -0.19509, -0.382683, -0.55557, -0.707107, -0.83147, \
    -0.92388, -0.980785, -1, -0.980785, -0.92388, -0.83147, -0.707107, \
    -0.55557, -0.382683, -0.19509, 0, 0.19509, 0.382683, 0.55557, \
    0.707107, 0.83147, 0.92388, 0.980785 }

#define INV_SQRTDCT_SIZE (real_t) 0.3535533906 
#define SQRT2_INV_SQRTDCT (real_t) 0.5 

void dct_2d(element_t* matrix_in, element_t* matrix_out) {
    real_t cu, cv, sum, cos_u, cos_v;
    int u, v, i, j;

    for (u = 0; u < DCT_SIZE; u++) {
        cu = u == 0 ? INV_SQRTDCT_SIZE : SQRT2_INV_SQRTDCT;
        for (v = 0; v < DCT_SIZE; v++) {
            cv = v == 0 ? INV_SQRTDCT_SIZE : SQRT2_INV_SQRTDCT; 
            sum = 0;
            for (i = 0; i < DCT_SIZE; i++) {
                cos_u = DCT_COS_TABLE[((2 * i + 1) * u) % DCT_COS_TABLE_SIZE];
                for (j = 0; j < DCT_SIZE; j++) { 
                    cos_v = DCT_COS_TABLE[((2 * j + 1) * v) % DCT_COS_TABLE_SIZE];
                    sum += matrix_in[i * DCT_SIZE + j] * cos_u * cos_v;
                }
            }
            matrix_out[u * DCT_SIZE + v] = cu * cv * sum;
        }
    }
}


void populate_mock_matrices(element_t** mock_matrices) {
    for (long i = 0; i < TOTAL_DCT_BLOCKS; i++) {
        for (int j = 0; j < DCT_SIZE; j++) {
            for (int k = 0; k < DCT_SIZE; k++) {
                mock_matrices[i][j * DCT_SIZE + k] = j + k;
            }
        }
    }
}


element_t** generate_mock_matrices() {
    element_t **mock_matrices = (element_t **) malloc(TOTAL_DCT_BLOCKS * sizeof(element_t*));
    for (int i = 0; i < TOTAL_DCT_BLOCKS; i++) {
        mock_matrices[i] = (element_t *) malloc(DCT_SIZE * DCT_SIZE * sizeof(element_t));
    }

    populate_mock_matrices(mock_matrices);
    return mock_matrices;
}

void free_mock_matrices(element_t** mock_matrices) { 
    for (int i = 0; i < TOTAL_DCT_BLOCKS; i++) {
        free(mock_matrices[i]);
    }
    free(mock_matrices);
}

int main() {
    element_t **mock_matrices = generate_mock_matrices();
    int i;
    
    element_t* matrix_out = (element_t *) malloc(DCT_SIZE * DCT_SIZE * sizeof(element_t));
    
    for(i = 0; i < TOTAL_DCT_BLOCKS; i++) {
        dct_2d(mock_matrices[i], matrix_out);
    }
    
    free_mock_matrices(mock_matrices);

    free(matrix_out);

    return 0;
}