------- 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
movl (%edi,%edx,4), %eax
movl %edx, -296(%ebp)
movl %edx, -576(%ebp)
xorl %eax, %ecx
movl (%edi,%ecx,4), %eax
movl %ecx, -292(%ebp)
movl %ecx, -580(%ebp)
xorl %eax, %esi
movl -400(%ebp), %eax
movl (%edi,%esi,4), %edx
movl %esi, -288(%ebp)
movl %esi, -396(%ebp)
movl -412(%ebp), %esi
xorl %edx, %eax
movl -404(%ebp), %edx
movl (%edi,%eax,4), %ecx
movl %eax, -284(%ebp)
movl %eax, -400(%ebp)
xorl %ecx, %edx
movl -408(%ebp), %ecx
movl (%edi,%edx,4), %eax
movl %edx, -280(%ebp)
movl %edx, -404(%ebp)
xorl %eax, %ecx
movl (%edi,%ecx,4), %eax
movl %ecx, -276(%ebp)
movl %ecx, -408(%ebp)
xorl %eax, %esi
movl -416(%ebp), %eax
movl (%edi,%esi,4), %edx
movl %esi, -272(%ebp)
movl %esi, -412(%ebp)
xorl %edx, %eax
movl %eax, -268(%ebp)
movl (%edi,%eax,4), %ecx
movl -420(%ebp), %edx
movl %eax, -416(%ebp)
movl -428(%ebp), %esi
xorl %ecx, %edx
movl -424(%ebp), %ecx
movl (%edi,%edx,4), %eax
movl %edx, -264(%ebp)
movl %edx, -420(%ebp)
xorl %eax, %ecx
movl (%edi,%ecx,4), %eax
movl %ecx, -260(%ebp)
movl %ecx, -424(%ebp)
xorl %eax, %esi
movl -432(%ebp), %eax
movl (%edi,%esi,4), %edx
movl %esi, -256(%ebp)
movl %esi, -428(%ebp)
movl -444(%ebp), %esi
xorl %edx, %eax
movl -436(%ebp), %edx
movl (%edi,%eax,4), %ecx
movl %eax, -252(%ebp)
movl %eax, -432(%ebp)
xorl %ecx, %edx
movl -440(%ebp), %ecx
movl (%edi,%edx,4), %eax
movl %edx, -248(%ebp)
movl %edx, -436(%ebp)
xorl %eax, %ecx
movl (%edi,%ecx,4), %eax
movl %ecx, -244(%ebp)
movl %ecx, -440(%ebp)
xorl %eax, %esi
movl -448(%ebp), %eax
movl (%edi,%esi,4), %edx
movl %esi, -240(%ebp)
movl %esi, -444(%ebp)
xorl %edx, %eax
movl -452(%ebp), %edx
movl (%edi,%eax,4), %ecx
movl %eax, -236(%ebp)
movl %eax, -448(%ebp)
xorl %ecx, %edx
movl %edx, -232(%ebp)
movl (%edi,%edx,4), %eax
movl -460(%ebp), %ecx
movl -468(%ebp), %esi
movl %edx, -452(%ebp)
xorl %eax, %ecx
movl (%edi,%ecx,4), %eax
movl %ecx, -228(%ebp)
movl %ecx, -460(%ebp)
xorl %eax, %esi
movl -476(%ebp), %eax
movl (%edi,%esi,4), %edx
movl %esi, -224(%ebp)
movl %esi, -468(%ebp)
movl -500(%ebp), %esi
xorl %edx, %eax
movl -484(%ebp), %edx
movl (%edi,%eax,4), %ecx
movl %eax, -220(%ebp)
movl %eax, -476(%ebp)
xorl %ecx, %edx
movl -492(%ebp), %ecx
movl (%edi,%edx,4), %eax
movl %edx, -216(%ebp)
movl %edx, -484(%ebp)
xorl %eax, %ecx
movl (%edi,%ecx,4), %eax
movl %edx, -216(%ebp)
movl %edx, -484(%ebp)
xorl %eax, %ecx
movl (%edi,%ecx,4), %eax
movl %ecx, -212(%ebp)
movl %ecx, -492(%ebp)
xorl %eax, %esi
movl -508(%ebp), %eax
movl (%edi,%esi,4), %edx
movl %esi, -380(%ebp)
movl %esi, -500(%ebp)
xorl %edx, %eax
movl -516(%ebp), %edx
movl (%edi,%eax,4), %esi
movl %eax, -376(%ebp)
movl %eax, -508(%ebp)
xorl %esi, %edx
movl -524(%ebp), %esi
movl (%edi,%edx,4), %ecx
movl %edx, -372(%ebp)
movl %edx, -516(%ebp)
xorl %ecx, %esi
movl %esi, -524(%ebp)
movl -532(%ebp), %ecx
movl (%edi,%esi,4), %edx
xorl %edx, %ecx
movl -540(%ebp), %edx
movl (%edi,%ecx,4), %eax
movl %ecx, -532(%ebp)
xorl %eax, %edx
movl -548(%ebp), %eax
xorl (%edi,%edx,4), %eax
movl %edx, -540(%ebp)
movl %eax, -584(%ebp)
movl %eax, -548(%ebp)
movl (%edi,%eax,4), %eax
xorl %eax, -208(%ebp)
cmpl $17, -384(%ebp)
jne .L16
=============================================================
The loop was unrolled, but it's clear that the address mode selection is worse.
--
What |Removed |Added
----------------------------------------------------------------------------
Status|UNCONFIRMED |NEW
Ever Confirmed| |1
Last reconfirmed|0000-00-00 00:00:00 |2005-06-01 22:55:36
date| |
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19923
