8192 要素の配列をループするとプログラムが突然遅くなるのはなぜですか?

#define SIZE 8192
float img[SIZE][SIZE]; // input image
float res[SIZE][SIZE]; // result of mean filter

int main() {
    // Initialization
    for (int i = 0; i < SIZE; i++) {
        for (int j = 0; j < SIZE; j++) {
            img[j][i] = (2 * j + i) % 8196;
        }
    }

    // Matrix processing - applying mean filter
    for (int i = 1; i < SIZE - 1; i++) {
        for (int j = 1; j < SIZE - 1; j++) {
            res[j][i] = 0;
            for (int k = -1; k < 2; k++) {
                for (int l = -1; l < 2; l++) {
                    res[j][i] += img[j + l][i + k];
                }
            }
            res[j][i] /= 9;
        }
    }
}

    for (int j = 1; j < SIZE - 1; j++) {
        for (int i = 1; i < SIZE - 1; i++) {
            res[j][i] = 0;
            for (int k = -1; k < 2; k++) {
                for (int l = -1; l < 2; l++) {
                    res[j][i] += img[j + l][i + k];
                }
            }
            res[j][i] /= 9;
        }
    }