int sum_array(int16_t *array, int size)
{
    int i;
    int res = 0;

    for(i=0;i<size;i++){
        res += array[i];

    }

    return res;
}

/* return the sum of all elements in an array. This works by calculating 4
totals (one for each lane) and adding those at the end to get the final total */
int sum_array_neon(int16_t *array, int size)
{
/* initialize the accumulator vector to zero */
int32x2_t acc1;
int64x1_t acc2;
/* this implementation assumes the size of the array is a multiple of 4 */
assert((size % 4) == 0);
/* counting backwards gives better code */
for (; size != 0; size -= 4)
{
int16x4_t vec;
/* load 4 values in parallel from the array */
vec = vld1_s16(array);
/* increment the array pointer to the next element */
array += 4;
/* add the vector to the accumulator vector */
acc = vadd_s16(acc, vec);
}
/* calculate the total */
acc1 = vpaddl_s16(acc);
acc2 = vpaddl_s32(acc1);
/* return the total as an integer */
return (int)vget_lane_s64(acc2, 0);
}

-mfpu=neon -mfloat-abi=softfp  -O3