Question

We trying to do some SSE operations, however, at the end of add_sse function, we trying to read back the value just computed, it will give us a seg fault. BUT, if we just print the value in the for loop, the result is ok.
Also it is ok to just read the element 0 in each array. read element 1 and beyond will cause seg fault.

Could any one help us to identify the problem? we tried everything, but still dont understand we there would be a seg fault. THanks

void main()
{
    ResultCounter *c_sse=(ResultCounter *)memalign(16,sizeof(ResultCounter)*4);    

    resetCounter (c_sse);  //initial struct to all 0

    add_sse (1,2, 3,4, c_sse);
}

void add_sse (unsigned int first, unsigned int second, unsigned int third, unsigned int fourth, ResultCounter *c)
{
    __attribute__((align(16))) int m_intarray[4] = {first, second, third,fourth};

    __attribute__((align(16))) int m_Larray[4] = {c[0].L, c[1].L, c[2].L,c[3].L};
    __attribute__((align(16))) int m_Marray[4] = {c[0].M, c[1].M, c[2].M,c[3].M};
    __attribute__((align(16))) int m_Harray[4] = {c[0].H, c[1].H, c[2].H,c[3].H};

    __m128i N = _mm_load_si128(&m_intarray[0]);
    __m128i L = _mm_load_si128(&m_Larray[0]);
    __m128i M = _mm_load_si128(&m_Marray[0]);
    __m128i H = _mm_load_si128(&m_Harray[0]);

    __m128i Lcarry = _mm_and_si128 (L, N);

    L = _mm_xor_si128 (L, N);

    __m128i Mcarry = _mm_and_si128 (M, Lcarry); 

    M = _mm_xor_si128 (M, Lcarry);

    H = _mm_or_si128 (H,Mcarry);

    _mm_store_si128(&m_Larray[0], L);
    _mm_store_si128(&m_Marray[0], M);
    _mm_store_si128(&m_Harray[0], H);

    for(i = 0; i < 4; i++) {
        //printf ("L:%d,addr=%u,M:%u,addr=%u,H:%u,addr=%u\n",m_Larray[i],&m_Larray[i],m_Marray[i],&m_Marray[i],m_Harray[i],&m_Harray[i]);
        c[i].L=m_Larray[i];
        c[i].M=m_Marray[i];
        c[i].H=m_Harray[i];
    }
}

//The struct used in main function.
typedef struct
{
    unsigned int L;
    unsigned int M;
    unsigned int H;
} ResultCounter;

Answer 1

The problem is that the ResultCounter struct is 12 bytes in size, so although the first element of your array, c[0] is 16 byte aligned, the second element, c[1], is not. The quickest/easiest fix for now would be to add 4 bytes of padding to this struct, e.g. an additional unused int:

typedef struct
{
    unsigned int L;
    unsigned int M;
    unsigned int H;
    unsigned int unused;
} ResultCounter;