Is it a gcc -O2 optimization bug (different result from -O1)?

I write a very simple program, it behaves normal without -O2:

#include <stdio.h>#include <stdint.h>int main(){    uint32_t A[4] = { 1, 2, 3, 4 };    float B[4] = { 0, 0, 0, 0 };    float C[4] = { 5, 6, 7, 8 };    int i;    // convert integer A to float B    for (i = 0; i < 4; i++)         B[i] = (float)A[i];    // memory copy from B to C    uint32_t *src = (uint32_t*)(B);    uint32_t *dst = (uint32_t*)(C);    dst[0] = src[0];    dst[1] = src[1];    dst[2] = src[2];    dst[3] = src[3];#if 0    // open this to correct the error    __asm__("":::"memory");#endif    // print C, C should be [1.0, 2.0, 3.0, 4.0]    for (i = 0; i < 4; i++)         printf("%f\n", C[i]);    return 0;}

Compile without -O2:

$ gcc error.c -o error$ ./error1.00002.00003.00004.0000

It works as expected. But if I added a -O2:

$ gcc -O2 error.c -o error$ ./error-6169930235904.0000000.000000-6169804406784.0000000.000000

In addition, if you switch #if 0 to #if 1 , it works correctly again. The asm ("":::"memory") should be unecessary in the same thread.

Is it a bug of -O2 optimization ??

Is there any thing I can tell the compiler to care of it ?? I have a function to store xmm register to a (void*) pointer, like:

inline void StoreRegister(void *ptr, const __m128& reg){#if DONT_HAVE_SSE    const uint32_t *src = reinterpret_cast<const uint32_t*>(&reg);    uint32_t *dst = reinterpret_cast<uint32_t*>(ptr);    dst[0] = src[0];    dst[1] = src[1];    dst[2] = src[2];    dst[3] = src[3];#else    _mm_storeu_si128(reinterpret_cast<__m128*>(ptr), _mm_castps_si128(reg));#endif}

The dst is the C in the code above, any way to make it correct without modifying the function signature.