------- Comment #9 from ubizjak at gmail dot com 2007-04-03 13:32 -------
(In reply to comment #8)
> what's the generated code for -ffast-math? in principle i don't see a reason
> why it should make any difference...
Trying to answer your question, I have played a bit with compile flags and
things are getting really strange:
[EMAIL PROTECTED] test]$ gcc -O2 -mfpmath=387 pr19780.c
[EMAIL PROTECTED] test]$ time ./a.out
Start?
Stop!
Result = 0.000000, 0.000000, 1.000000
real 0m1.211s
user 0m1.212s
sys 0m0.004s
[EMAIL PROTECTED] test]$ gcc -O2 -mfpmath=387 -msse pr19780.c
[EMAIL PROTECTED] test]$ time ./a.out
Start?
Stop!
Result = 0.000000, 0.000000, 1.000000
real 0m0.555s
user 0m0.552s
sys 0m0.004s
Note that -msse should have no effect on calculations. The difference between
asm dumps is:
--- pr19780.s 2007-04-03 14:28:14.000000000 +0200
+++ pr19780.s_ 2007-04-03 14:28:01.000000000 +0200
@@ -17,69 +17,61 @@
pushl %ebp
movl %esp, %ebp
pushl %ecx
- subl $84, %esp
+ subl $100, %esp
movl $.LC0, (%esp)
call puts
xorl %eax, %eax
- fldz
fld1
fsts -16(%ebp)
+ fldz
+ fsts -12(%ebp)
+ fld %st(0)
fld %st(1)
- fld %st(2)
- fld %st(3)
jmp .L2
.p2align 4,,7
.L7:
- fstp %st(5)
- fstp %st(0)
- fxch %st(1)
- fxch %st(2)
- fxch %st(3)
- fxch %st(4)
fxch %st(3)
+ fxch %st(2)
.L2:
- fld %st(1)
+ fld %st(2)
addl $1, %eax
- fmul %st(3), %st
+ fmul %st(1), %st
cmpl $100000000, %eax
- fstps -12(%ebp)
+ flds -12(%ebp)
+ fmul %st(5), %st
+ fsubrp %st, %st(1)
+ flds -12(%ebp)
+ fmul %st(3), %st
flds -16(%ebp)
- fmul %st(1), %st
- fsubrs -12(%ebp)
- fstps -12(%ebp)
- fmul %st(4), %st
- fld %st(3)
fmul %st(3), %st
fsubrp %st, %st(1)
flds -16(%ebp)
- fmulp %st, %st(4)
- fxch %st(1)
+ fmul %st(6), %st
+ fxch %st(5)
fmul %st(4), %st
- fsubrp %st, %st(3)
- flds -16(%ebp)
- fld %st(3)
+ fsubrp %st, %st(5)
fxch %st(2)
- fsts -16(%ebp)
- flds -12(%ebp)
+ fstps -12(%ebp)
+ fxch %st(2)
+ fstps -16(%ebp)
jne .L7
- fstp %st(0)
- fstp %st(5)
- fstp %st(0)
- fstp %st(0)
- fstp %st(0)
+ fstp %st(3)
+ fxch %st(1)
movl $.LC3, (%esp)
fstps -40(%ebp)
+ fxch %st(1)
fstps -56(%ebp)
+ fstps -72(%ebp)
call puts
flds -40(%ebp)
fstpl 20(%esp)
flds -56(%ebp)
fstpl 12(%esp)
- flds -12(%ebp)
+ flds -72(%ebp)
fstpl 4(%esp)
movl $.LC4, (%esp)
call printf
- addl $84, %esp
+ addl $100, %esp
xorl %eax, %eax
popl %ecx
popl %ebp
where (+++) is with -msse.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19780
