------- Additional Comments From rakdver at atrey dot karlin dot mff dot cuni
dot cz 2005-06-06 15:00 -------
Subject: Re: openssl is slower when compiled with gcc 4.0 than 3.3
> 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];
> }
> }
> =========================================================================
with the TARGET_MEM_REFs patch the result is much better. At
least we avoid the multiplication by 4
> leal 0(,%edi,4), %ecx
and other results of the DOM missoptimization of addressing modes, that was
one of the main motivations for TARGET_MEM_REFs.
We still use one more iv than in the 3.4 case, and in result we need one
more register.
.L2:
movl 8(%ebp), %edi
movl -4(%edi,%ecx,4), %eax
movl %eax, (%esi)
movl 16(%ebp), %edx
movzbl -1(%ecx,%edx), %eax
movl %eax, 64(%esi)
movl -4(%edi,%ecx,4), %edx
xorl %eax, %edx
movl %edx, 128(%esi)
xorl -20(%ebp), %eax
movl -16(%ebp), %edi
movl (%edi,%eax,4), %eax
movl 12(%ebp), %edx
xorl -4(%edx,%ecx,4), %eax
movl %eax, -4(%edx,%ecx,4)
movl %eax, -20(%ebp)
incl %ecx
addl $4, %esi
cmpl $17, %ecx
jne .L2
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
