------- Comment #6 from uros at kss-loka dot si 2006-08-16 12:15 -------
IMO the problem here is in IVopts. Using gcc-3.x, the innermost loop compiles
to:
.L15:
movl (%edi,%edx,4), %eax
fldl (%ebp,%edx,8)
addl $1, %edx
fmull (%esi,%eax,8)
cmpl %ecx, %edx
faddp %st, %st(1)
jl .L15
and with current SVN gcc-4.2 into:
.L12:
movl (%ecx), %eax
fldl (%ebp,%eax,8)
fmull (%edx)
faddp %st, %st(1)
addl $1, %ebx
addl $4, %ecx
addl $8, %edx
cmpl %esi, %ebx
jne .L12
Adding -fno-ivopts, this loop gets compiled into:
.L12:
movl (%edi,%edx,4), %eax
fldl (%esi,%eax,8)
fmull (%ebp,%edx,8)
faddp %st, %st(1)
addl $1, %edx
cmpl %edx, %ecx
jg .L12
Timings (-O3 -march=pentium4 -fomit-frame-pointer):
gcc-3.2: 0m2.301s
gcc-4.2: 0m2.713s
gcc-4.2 + -fno-ivopts: 0m2.473s
with:
gcc version 3.2 20020903 (Red Hat Linux 8.0 3.2-7)
gcc version 4.2.0 20060816 (experimental)
I think that remaining time difference is due to strange loop above innermost:
gcc-3.2:
fld %st(0)
.L16:
movl 36(%esp), %eax
fld %st(0)
movl 4(%eax,%ebx,4), %ecx
movl (%eax,%ebx,4), %edx
cmpl %ecx, %edx
jge .L23
.L15:
movl (%edi,%edx,4), %eax
fldl (%ebp,%edx,8)
addl $1, %edx
fmull (%esi,%eax,8)
cmpl %ecx, %edx
faddp %st, %st(1)
jl .L15
.L23:
movl 28(%esp), %eax
fstpl (%eax,%ebx,8)
addl $1, %ebx
cmpl 24(%esp), %ebx
jl .L16
========
gcc-4.2:
.L8:
movl 36(%esp), %edx
movl (%edx,%edi,4), %eax
movl 4(%edx,%edi,4), %esi
fldz
cmpl %esi, %eax
jge .L11
fstp %st(0)
movl 40(%esp), %ebx
leal (%ebx,%eax,4), %ecx
movl 32(%esp), %ebx
leal (%ebx,%eax,8), %edx
fldz
xorl %ebx, %ebx
subl %eax, %esi
.L12:
movl (%ecx), %eax
fldl (%ebp,%eax,8)
fmull (%edx)
faddp %st, %st(1)
addl $1, %ebx
addl $4, %ecx
addl $8, %edx
cmpl %esi, %ebx
jne .L12
.L11:
movl 28(%esp), %eax
fstpl (%eax,%edi,8)
addl $1, %edi
cmpl 24(%esp), %edi
jne .L8
========
and gcc-4.2 -fno-ivopts:
.L8:
leal (%ebx,%ebx), %eax
movl 40(%esp), %edx
movl (%edx,%eax,2), %edx
movl %edx, (%esp)
movl 40(%esp), %edx
movl 4(%edx,%eax,2), %ecx
fldz
cmpl %ecx, (%esp)
jge .L11
fstp %st(0)
movl (%esp), %edx
fldz
.L12:
movl (%edi,%edx,4), %eax
fldl (%esi,%eax,8)
fmull (%ebp,%edx,8)
faddp %st, %st(1)
addl $1, %edx
cmpl %edx, %ecx
jg .L12
.L11:
movl 32(%esp), %ecx
fstpl (%ecx,%ebx,8)
addl $1, %ebx
cmpl %ebx, 28(%esp)
jg .L8
--
uros at kss-loka dot si changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |uros at kss-loka dot si
Status|UNCONFIRMED |NEW
Ever Confirmed|0 |1
Last reconfirmed|0000-00-00 00:00:00 |2006-08-16 12:15:56
date| |
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=21676
