is -O2 breaking sse2 alignment?

[JP Fournier]

Hi All.

In the example below, compiling with -O2 results in incorrect output 
from the program.  -O seems OK.  Am I missing something alignment wise 
(or otherwise) or is -O2 breaking my alignment?

If I use  _mm_storeu_si128 then both -O2 and -O work as expected.

Any thoughts appreciated.

jp

------

bash-3.1$ gcc -O -msse2 -o sse2 sse2.c
bash-3.1$ ./sse2
c0=2 c1=2
bash-3.1$ gcc -O2 -msse2 -o sse2 sse2.c
bash-3.1$ ./sse2
c0=0 c1=0
bash-3.1$ gcc --version
gcc (GCC) 4.1.2
bash-3.1$ uname -a
Linux puma 2.6.22.8 #1 SMP Tue Sep 25 20:41:25 BST 2007 x86_64 x86_64 
x86_64 GNU/Linux

sse2.c:

#include <stdio.h>
#include <emmintrin.h>

void test_int() {

        // array of 2 8 byte ints
        long int *a  = _mm_malloc(16, 16);
        long int *b  = _mm_malloc(16, 16);
        long int *c  = _mm_malloc(16, 16);

        __m128i ai __attribute__ ((aligned (16)));
        __m128i bi __attribute__ ((aligned (16)));
        __m128i ci __attribute__ ((aligned (16)));

        a[0] = a[1] = 1;
        b[0] = b[1] = 1;
        c[0] = c[1] = 0;

        ai = _mm_load_si128( (__m128i *) (void*)a );
        bi = _mm_load_si128( (__m128i *) (void*)b );

        ci = _mm_add_epi8( ai, bi );
        _mm_store_si128( (__m128i *) (void*)c, ci );
        printf("c0=%ld c1=%ld\n", c[0], c[1] );
}

int main( int count, char ** args ) {
     test_int();
     return 0;
}