[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From steven at gcc dot gnu dot org 2005-06-06 07:16 --- Could L1 icache blow-out be the reason? -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From rakdver at atrey dot karlin dot mff dot cuni dot cz 2005-06-06 07:30 --- Subject: Re: openssl is slower when compiled with gcc 4.0 than 3.3 Could L1 icache blow-out be the reason? This is not likely with the minimized example. -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From giovannibajo at libero dot it 2005-06-06 13:33 --- Uhm, at this point, I don't believe anymore that the loop I posted is the cause of the regression. Maybe the regression is somewhere else. I'll investigate. -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- 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:
movl8(%ebp), %esi
movl(%esi,%ecx,4), %eax
movl%eax, [EMAIL PROTECTED](%ebx,%ecx,4)
movl16(%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:
movl8(%ebp), %eax
leal0(,%edi,4), %ecx
movl%ecx, -28(%ebp)
addl%ecx, %eax
movl16(%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
movl12(%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
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- 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
leal0(,%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:
movl8(%ebp), %edi
movl-4(%edi,%ecx,4), %eax
movl%eax, (%esi)
movl16(%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
movl12(%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
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From rakdver at atrey dot karlin dot mff dot cuni dot cz 2005-06-02 08:01 --- Subject: Re: openssl is slower when compiled with gcc 4.0 than 3.3 The assembler attributed to 4.0 was produced by mainline (or some patched version of 4.0), wasn't it? Otherwise I cannot imagine why the inner loop would be unrolled. For plain 4.0, we get the following code, which seems just fine and equivalent to the one obtained with 3.4 (one of the memory references is strength reduced, but since we still fit into registers, this is OK). I don't just now see what/whether there is some problem with the code produced by 4.1, but I also don't see anything related to addressing mode selection there. .L21: movl[EMAIL PROTECTED](%ebx,%eax,4), %eax xorl(%edx), %eax movl%eax, (%edx) movl[EMAIL PROTECTED](%ebx,%eax,4), %eax xorl4(%edx), %eax movl%eax, 4(%edx) movl[EMAIL PROTECTED](%ebx,%eax,4), %eax xorl8(%edx), %eax movl%eax, 8(%edx) movl[EMAIL PROTECTED](%ebx,%eax,4), %eax xorl12(%edx), %eax movl%eax, 12(%edx) movl[EMAIL PROTECTED](%ebx,%eax,4), %eax xorl16(%edx), %eax movl%eax, 16(%edx) movl[EMAIL PROTECTED](%ebx,%eax,4), %eax xorl20(%edx), %eax movl%eax, 20(%edx) movl[EMAIL PROTECTED](%ebx,%eax,4), %eax xorl24(%edx), %eax movl%eax, 24(%edx) movl[EMAIL PROTECTED](%ebx,%eax,4), %eax xorl28(%edx), %eax movl%eax, 28(%edx) addl$32, %edx leal-12(%ebp), %esi cmpl%esi, %edx jne .L21 -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From yx at cs dot ucla dot edu 2005-06-01 20:47 --- When we ran 'openssh speed md2', we did see that gcc-4.0 was slower than earlier versions, so we created a minimal test case, which we will attach. Here is how long it took to run a 34 megabyte file through the test program when compiled with various compilers and options: gcc-2.95.3 -fPIC -O1 4.940s gcc-4.0.0 -fPIC -O1 3.510s gcc-3.4.3 -fPIC -O1 5.190s gcc-2.95.3 -fPIC -O2 3.470s gcc-3.4.3 -fPIC -O2 3.460s gcc-4.0.0 -fPIC -O2 4.050s gcc-2.95.3 -fPIC -O3 3.400s gcc-3.4.3 -fPIC -O3 3.740s gcc-4.0.0 -fPIC -O3 4.010s This test was done on a pentium 4 workstation, and no smoothing was done on the resulting times, but they seemed to be repeatable. We also tried without -fPIC, but did not see as large a regression there. -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From pinskia at gcc dot gnu dot org 2005-06-01 20:55 --- I would not doubt this is just not using the i386 address mode -- What|Removed |Added Status|RESOLVED|UNCONFIRMED Resolution|INVALID | http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From giovannibajo at libero dot it 2005-06-01 22:55 --- Confirmed. The regression appears only with -fPIC, and it's pretty evident. The core is md2_block, the inner loop: GCC 3.4 = .L29: xorl%edx, %edx .p2align 2,,3 .L28: movl[EMAIL PROTECTED](%ebx,%eax,4), %esi xorl-216(%ebp,%edx,4), %esi movl[EMAIL PROTECTED](%ebx,%esi,4), %eax xorl-212(%ebp,%edx,4), %eax movl[EMAIL PROTECTED](%ebx,%eax,4), %edi xorl-208(%ebp,%edx,4), %edi movl%esi, -216(%ebp,%edx,4) movl[EMAIL PROTECTED](%ebx,%edi,4), %esi xorl-204(%ebp,%edx,4), %esi movl%eax, -212(%ebp,%edx,4) movl[EMAIL PROTECTED](%ebx,%esi,4), %eax xorl-200(%ebp,%edx,4), %eax movl%edi, -208(%ebp,%edx,4) movl[EMAIL PROTECTED](%ebx,%eax,4), %edi xorl-196(%ebp,%edx,4), %edi movl%esi, -204(%ebp,%edx,4) movl[EMAIL PROTECTED](%ebx,%edi,4), %esi xorl-192(%ebp,%edx,4), %esi movl%eax, -200(%ebp,%edx,4) movl[EMAIL PROTECTED](%ebx,%esi,4), %eax xorl-188(%ebp,%edx,4), %eax movl%edi, -196(%ebp,%edx,4) movl%esi, -192(%ebp,%edx,4) movl%eax, -188(%ebp,%edx,4) addl$8, %edx cmpl$47, %edx jle .L28 addl%ecx, %eax incl%ecx andl$255, %eax cmpl$17, %ecx jle .L29 = GCC 4.0 = .L16: movl-384(%ebp), %eax movl-208(%ebp), %esi incl-384(%ebp) addl%esi, %eax movl-456(%ebp), %esi andl$255, %eax movl(%edi,%eax,4), %ecx movl-464(%ebp), %eax xorl%ecx, %esi movl(%edi,%esi,4), %edx movl%esi, -368(%ebp) movl%esi, -456(%ebp) movl-488(%ebp), %esi xorl%edx, %eax movl-472(%ebp), %edx movl(%edi,%eax,4), %ecx movl(%edi,%eax,4), %ecx movl%eax, -364(%ebp) movl%eax, -464(%ebp) xorl%ecx, %edx movl-480(%ebp), %ecx movl(%edi,%edx,4), %eax movl%edx, -360(%ebp) movl%edx, -472(%ebp) xorl%eax, %ecx movl(%edi,%ecx,4), %eax movl%ecx, -356(%ebp) movl%ecx, -480(%ebp) xorl%eax, %esi movl-496(%ebp), %eax movl(%edi,%esi,4), %edx movl%esi, -352(%ebp) movl%esi, -488(%ebp) xorl%edx, %eax movl-504(%ebp), %edx movl(%edi,%eax,4), %ecx movl%eax, -348(%ebp) movl%eax, -496(%ebp) xorl%ecx, %edx movl-512(%ebp), %ecx movl(%edi,%edx,4), %eax movl%edx, -344(%ebp) movl%edx, -504(%ebp) xorl%eax, %ecx movl%ecx, -340(%ebp) movl(%edi,%ecx,4), %eax movl-520(%ebp), %esi movl%ecx, -512(%ebp) xorl%eax, %esi movl-528(%ebp), %eax movl(%edi,%esi,4), %edx movl%esi, -336(%ebp) movl%esi, -520(%ebp) movl-552(%ebp), %esi xorl%edx, %eax movl-536(%ebp), %edx movl(%edi,%eax,4), %ecx movl%eax, -332(%ebp) movl%eax, -528(%ebp) xorl%ecx, %edx movl-544(%ebp), %ecx movl(%edi,%edx,4), %eax movl%edx, -328(%ebp) movl%edx, -536(%ebp) xorl%eax, %ecx movl(%edi,%ecx,4), %eax movl%ecx, -324(%ebp) movl%ecx, -544(%ebp) xorl%eax, %esi movl-556(%ebp), %eax movl(%edi,%esi,4), %edx movl%esi, -320(%ebp) movl%esi, -552(%ebp) movl-568(%ebp), %esi xorl%edx, %eax movl-560(%ebp), %edx movl(%edi,%eax,4), %ecx movl%eax, -316(%ebp) movl%eax, -556(%ebp) xorl%ecx, %edx movl-564(%ebp), %ecx movl(%edi,%edx,4), %eax movl%edx, -312(%ebp) movl%edx, -560(%ebp) xorl%eax, %ecx movl(%edi,%ecx,4), %eax movl%ecx, -308(%ebp) movl%ecx, -564(%ebp) xorl%eax, %esi movl%esi, -304(%ebp) movl(%edi,%esi,4), %edx movl-572(%ebp), %eax movl%esi, -568(%ebp) movl-396(%ebp), %esi xorl%edx, %eax movl-576(%ebp), %edx movl(%edi,%eax,4), %ecx movl%eax, -300(%ebp) movl%eax, -572(%ebp) xorl%ecx, %edx movl-580(%ebp), %ecx
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From giovannibajo at libero dot it 2005-06-01 22:59 --- I wonder if this is fixed by TARGET_MEM_REF. -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From pinskia at gcc dot gnu dot org 2005-05-14 20:36 --- No feedback in 3 months. -- What|Removed |Added Status|WAITING |RESOLVED Resolution||INVALID http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
-- What|Removed |Added Component|c |target Keywords||missed-optimization http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
[Bug target/19923] openssl is slower when compiled with gcc 4.0 than 3.3
--- Additional Comments From pinskia at gcc dot gnu dot org 2005-02-12 22:24 --- We need a self contained example. -- What|Removed |Added CC||pinskia at gcc dot gnu dot ||org Status|UNCONFIRMED |WAITING http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
