[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3

[giovannibajo at libero dot it]

------- Additional Comments From giovannibajo at libero dot it  2005-06-06 
14:40 -------
Looks like the culrpit is this:

=========================================================================
static unsigned int S[256];
unsigned
md2_block (unsigned int *sp1, unsigned int *sp2, const unsigned char *d)
{
        register unsigned int t;
        register int i, j;
        static unsigned int state[48];

        j = sp2[16 - 1];
        for (i = 0; i < 16; i++)
        {
                state[i] = sp1[i];
                state[i + 16] = t = d[i];
                state[i + 32] = (t ^ sp1[i]);
                j = sp2[i] ^= S[t ^ j];
        }
}
=========================================================================


gcc 3.4.3 -fPIC -O2:
===================================================
.L5:
        movl    8(%ebp), %esi
        movl    (%esi,%ecx,4), %eax
        movl    %eax, [EMAIL PROTECTED](%ebx,%ecx,4)
        movl    16(%ebp), %edx
        movzbl  (%edx,%ecx), %eax
        movl    %eax, [EMAIL PROTECTED](%ebx,%ecx,4)
        movl    (%esi,%ecx,4), %edx
        xorl    %eax, %edx
        movl    -16(%ebp), %esi
        xorl    -20(%ebp), %eax
        movl    %edx, [EMAIL PROTECTED](%ebx,%ecx,4)
        movl    (%esi,%eax,4), %eax
        xorl    (%edi,%ecx,4), %eax
        movl    %eax, (%edi,%ecx,4)
        incl    %ecx
        cmpl    $15, %ecx
        movl    %eax, -20(%ebp)
        jle     .L5
===================================================



gcc 4.1.0 20050529 -fPIC -O2:
===================================================
.L2:
        movl    8(%ebp), %eax
        leal    0(,%edi,4), %ecx
        movl    %ecx, -28(%ebp)
        addl    %ecx, %eax
        movl    16(%ebp), %ecx
        movl    %eax, %edx
        movl    %eax, -24(%ebp)
        movl    -4(%eax), %eax
        movl    %eax, (%esi)
        movzbl  -1(%ecx,%edi), %eax
        incl    %edi
        movl    %eax, 64(%esi)
        movl    -4(%edx), %ecx
        movl    12(%ebp), %edx
        xorl    %eax, %ecx
        movl    %ecx, 128(%esi)
        movl    -28(%ebp), %ecx
        addl    $4, %esi
        addl    %edx, %ecx
        movl    -16(%ebp), %edx
        xorl    %edx, %eax
        movl    -20(%ebp), %edx
        movl    (%edx,%eax,4), %eax
        movl    -4(%ecx), %edx
        xorl    %edx, %eax
        cmpl    $17, %edi
        movl    %eax, -4(%ecx)
        movl    %eax, -16(%ebp)
        jne     .L2
===================================================


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923