------- Comment #64 from lucier at math dot purdue dot edu 2009-05-06 20:43
-------
In answer to comment 60, here's the command line where I added
-fforward-propagate -fno-move-loop-invariants:
/pkgs/gcc-mainline/bin/gcc -save-temps -I../include -I. -Wall -W -Wno-unused
-O1 -fno-math-errno -fschedule-insns2 -fno-trapping-math -fno-strict-aliasing
-fwrapv -fomit-frame-pointer -fPIC -fno-common -mieee-fp -fforward-propagate
-fno-move-loop-invariants -DHAVE_CONFIG_H -D___PRIMAL -D___LIBRARY
-D___GAMBCDIR="\"/usr/local/Gambit-C/v4.1.2\"" -D___SYS_TYPE_CPU="\"x86_64\""
-D___SYS_TYPE_VENDOR="\"unknown\"" -D___SYS_TYPE_OS="\"linux-gnu\"" -c _num.c
here's the compiler:
/pkgs/gcc-mainline/bin/gcc -v
Using built-in specs.
Target: x86_64-unknown-linux-gnu
Configured with: /tmp/lucier/gcc/mainline/configure --enable-checking=release
--prefix=/pkgs/gcc-mainline --enable-languages=c
Thread model: posix
gcc version 4.5.0 20090506 (experimental) [trunk revision 147199] (GCC)
and the runtime didn't change (substantially)
132 ms cpu time (132 user, 0 system)
and the loop looks pretty much just as bad (it's 117 instructions long, by my
count):
.L2752:
movq %rcx, %rdx
addq 8(%rax), %rdx
leaq 4(%rcx), %rdi
movq %rdx, -8(%rax)
leaq 4(%rdx), %rbx
addq 8(%rax), %rdx
movq %rbx, -16(%rax)
movq %rdx, -24(%rax)
leaq 4(%rdx), %rbx
addq 8(%rax), %rdx
movq %rbx, -32(%rax)
movq %rdx, -40(%rax)
leaq 4(%rdx), %rbx
movq 40(%rax), %rdx
movq %rbx, -48(%rax)
movsd 7(%rdx,%rbx,2), %xmm9
movq -40(%rax), %rbx
leaq 7(%rdx,%rcx,2), %r8
addq $8, %rcx
movsd (%r8), %xmm4
cmpq %rcx, %r13
movsd 7(%rdx,%rbx,2), %xmm11
movq -32(%rax), %rbx
movsd 7(%rdx,%rbx,2), %xmm5
movq -24(%rax), %rbx
movsd 7(%rdx,%rbx,2), %xmm7
movq -16(%rax), %rbx
movsd 7(%rdx,%rbx,2), %xmm14
movq -8(%rax), %rbx
movsd 7(%rdx,%rbx,2), %xmm6
leaq (%rdi,%rdi), %rbx
movsd 7(%rbx,%rdx), %xmm8
movq 24(%rax), %rdx
movapd %xmm6, %xmm13
movsd 15(%rdx), %xmm1
movsd 7(%rdx), %xmm2
movapd %xmm1, %xmm10
movsd 31(%rdx), %xmm3
movapd %xmm2, %xmm12
mulsd %xmm11, %xmm10
mulsd %xmm9, %xmm12
mulsd %xmm2, %xmm11
mulsd %xmm1, %xmm9
movsd 23(%rdx), %xmm0
addsd %xmm12, %xmm10
movapd %xmm2, %xmm12
mulsd %xmm7, %xmm2
subsd %xmm9, %xmm11
movapd %xmm1, %xmm9
mulsd %xmm5, %xmm12
mulsd %xmm5, %xmm1
movapd %xmm8, %xmm5
mulsd %xmm7, %xmm9
movapd %xmm4, %xmm7
subsd %xmm11, %xmm13
addsd %xmm6, %xmm11
movsd .LC5(%rip), %xmm6
subsd %xmm1, %xmm2
movapd %xmm0, %xmm1
addsd %xmm12, %xmm9
movapd %xmm14, %xmm12
xorpd %xmm3, %xmm6
subsd %xmm10, %xmm12
mulsd %xmm13, %xmm1
subsd %xmm2, %xmm7
addsd %xmm4, %xmm2
movapd %xmm6, %xmm4
addsd %xmm14, %xmm10
mulsd %xmm13, %xmm6
mulsd %xmm12, %xmm4
subsd %xmm9, %xmm5
mulsd %xmm0, %xmm12
addsd %xmm8, %xmm9
movapd %xmm0, %xmm8
mulsd %xmm11, %xmm0
addsd %xmm1, %xmm4
movapd %xmm3, %xmm1
mulsd %xmm10, %xmm3
subsd %xmm12, %xmm6
mulsd %xmm11, %xmm1
mulsd %xmm10, %xmm8
subsd %xmm3, %xmm0
addsd %xmm1, %xmm8
movapd %xmm2, %xmm1
addsd %xmm0, %xmm1
subsd %xmm0, %xmm2
movapd %xmm7, %xmm0
subsd %xmm6, %xmm7
addsd %xmm6, %xmm0
movsd %xmm1, (%r8)
movapd %xmm9, %xmm1
movq 40(%rax), %rdx
subsd %xmm8, %xmm9
addsd %xmm8, %xmm1
movsd %xmm1, 7(%rbx,%rdx)
movq -8(%rax), %rbx
movq 40(%rax), %rdx
movsd %xmm2, 7(%rdx,%rbx,2)
movq -16(%rax), %rbx
movq 40(%rax), %rdx
movsd %xmm9, 7(%rdx,%rbx,2)
movq -24(%rax), %rbx
movq 40(%rax), %rdx
movsd %xmm0, 7(%rdx,%rbx,2)
movapd %xmm5, %xmm0
movq -32(%rax), %rbx
movq 40(%rax), %rdx
subsd %xmm4, %xmm5
addsd %xmm4, %xmm0
movsd %xmm0, 7(%rdx,%rbx,2)
movq -40(%rax), %rbx
movq 40(%rax), %rdx
movsd %xmm7, 7(%rdx,%rbx,2)
movq -48(%rax), %rbx
movq 40(%rax), %rdx
movsd %xmm5, 7(%rdx,%rbx,2)
jg .L2752
movq %rdi, %r13
.L2751:
--
lucier at math dot purdue dot edu changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|WAITING |NEW
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=33928
