Asm speed test - asm vs. compiler

[aewarnick]

void ColComparing()
{
    Col c1(100,100,100,240), c2(100,100,99,240);
    uint i, ii=0;

    asm volatile(
    ";"
    ::"r"(c1), "r"(c2), "r"(&ii):);

    ResetAndStartTimer("Asm ");
    for(i= 0; i<loops; ++i)
    {
        asm volatile(
        "cmpl %0,%1;"
        "jne endA;"
        "incl (%2);"
        "endA:;"
        ::"r"(c1), "r"(c2), "r"(&ii):);
    }
    StopAndLog();
DD(ii);
    ii=0;
    ResetAndStartTimer("4byte");
    for(i= 0; i<loops; ++i)
    {
        if(*((uint32*)&c1)==*((uint32*)&c2)) ++ii;
    }
    StopAndLog();
DD(ii);
    ii=0;
    ResetAndStartTimer("1byte");
    for(i= 0; i<loops; ++i)
    {
        if(c1.b == c2.b && c1.g == c2.g && c1.r == c2.r && c1.a==c2.a) ++ii;
    }
    StopAndLog();
DD(ii);
    testInt += c1.b+ii;
} 

Output:
Loops: 1410065408

Asm 1.359000
4byte 3.531000
1byte 1.828000

How is it that the 4byte comparison is so much slower?
It should exactly the same as the Asm.
I am using gcc with ALL optimizations turned on.