int shellOpti[16] = {1391376, 463792, 198768, 86961, 33936, 13776, 4592,1968, 861, 336, 112, 48, 21, 7, 3, 1};
int idx = blockIdx.x * blockDim.x + threadIdx.x;

if (idx < 16)
    {
        start = shellOpti[idx];
        for (i = start ; i < SIZE ; i++)
        {
            val = table[i];
            j = i;
            while (j >= start && table[j - start] > val)
            {
                table[j] = table[j - start];
                j = j - start;
            }
            table[j] = val;
        }
    }