Strange FP behaviour

[michael dot hiegemann at chkra dot mail dot abb dot com]

Hi folks,

My system is SuSE 6.4 (i386) - Kernel 2.2.14, P90 on ASUS P/I-P55TP4XE board,
libc.so.6

The following code (fp_bug.c) seems to be compiled incorrect:

#include <stdio.h>
#include <math.h>


double my_sqr (double y)
{
     return y * y;
}


int main ()
{
     double y, result, result2, delta;


     y       = 6.03856090847925908e-01;

     result  = (0.5 - my_sqr (y)) + 0.5;

     result2 = my_sqr (y);
     result2 = (0.5 - result2) + 0.5;

     delta   = fabs (result - result2);

     printf ("result  = %24.16e\n", result);
     printf ("result2 = %24.16e\n", result2);
     printf ("delta   = %24.16e\n", delta);

     return 1;
}


The program was compiled via

gcc -v fp_bug.c

and the compiler output is


Reading specs from /usr/lib/gcc-lib/i486-suse-linux/2.95.2/specs
gcc version 2.95.2 19991024 (release)
 /usr/lib/gcc-lib/i486-suse-linux/2.95.2/cpp -lang-c -v -D__GNUC__=2
-D__GNUC_MINOR__=95 -D__ELF__ -Dunix -D__i386__ -Dlinux -D__ELF__ -D__unix__
-D__i386__ -D__linux__ -D__unix -D__linux -Asystem(posix) -Wall -pedantic
-Acpu(i386) -Amachine(i386) -Di386 -D__i386 -D__i386__ -Di486 -D__i486
-D__i486__ fp_bug.c /tmp/cc2Auxw0.i
GNU CPP version 2.95.2 19991024 (release) (i386 Linux/ELF)
#include "..." search starts here:
#include <...> search starts here:
 /usr/local/include
 /usr/lib/gcc-lib/i486-suse-linux/2.95.2/include
 /usr/include
End of search list.
The following default directories have been omitted from the search path:
 /usr/include/g++
 /usr/lib/gcc-lib/i486-suse-linux/2.95.2/../../../../i486-suse-linux/include
End of omitted list.
 /usr/lib/gcc-lib/i486-suse-linux/2.95.2/cc1 /tmp/cc2Auxw0.i -quiet -dumpbase
fp_bug.c -Wall -pedantic -version -o /tmp/ccgR5is8.s
GNU C version 2.95.2 19991024 (release) (i486-suse-linux) compiled by GNU C
version 2.95.2 19991024 (release).
 /usr/i486-suse-linux/bin/as -V -Qy -o /tmp/ccxSoHuw.o /tmp/ccgR5is8.s
GNU assembler version 2.9.5 (i486-suse-linux) using BFD version 2.9.5.0.24
 /usr/lib/gcc-lib/i486-suse-linux/2.95.2/collect2 -m elf_i386 -dynamic-linker
/lib/ld-linux.so.2 /usr/lib/crt1.o /usr/lib/crti.o
/usr/lib/gcc-lib/i486-suse-linux/2.95.2/crtbegin.o
-L/usr/lib/gcc-lib/i486-suse-linux/2.95.2 -L/usr/i486-suse-linux/lib
/tmp/ccxSoHuw.o -lgcc -lc -lgcc /usr/lib/gcc-lib/i486-suse-linux/2.95.2/crtend.o
 /usr/lib/crtn.o


The program a.out generates the following output:

result  =  6.3535782154586140e-01
result2 =  6.3535782154586151e-01
delta   =  1.1102230246251565e-16


A friend tested it with his PII/400 system, ASUS P2B-B board, OS SuSE linux 6.4,
 Kernel 2.2.14.
He got the same program output, the compiler info is virtually the same and the
assembler output is identical.

We expect the delta to be exactly zero. Could you have a look at this?


Greetings from Switzerland,

Michael Hiegemann and Christoph Schilling




For sake of completeness, the assembler output (gcc -S fp_bug.c) is


     .file     "fp_bug.c"
     .version  "01.01"
gcc2_compiled.:
.text
     .align 16
.globl my_sqr
     .type      my_sqr,@function
my_sqr:
     pushl %ebp
     movl %esp,%ebp
     fldl 8(%ebp)
     fmull 8(%ebp)
     jmp .L2
     .p2align 4,,7
.L2:
     movl %ebp,%esp
     popl %ebp
     ret
.Lfe1:
     .size      my_sqr,.Lfe1-my_sqr
.section  .rodata
.LC2:
     .string   "result  = %24.16e\n"
.LC3:
     .string   "result2 = %24.16e\n"
.LC4:
     .string   "delta   = %24.16e\n"
     .align 8
.LC0:
     .long 0x235d4f7,0x3fe352ca
     .align 8
.LC1:
     .long 0x0,0x3fe00000
.text
     .align 16
.globl main
     .type      main,@function
main:
     pushl %ebp
     movl %esp,%ebp
     subl $40,%esp
     fldl .LC0
     fstpl -8(%ebp)
     addl $-8,%esp
     fldl -8(%ebp)
     subl $8,%esp
     fstpl (%esp)
     call my_sqr
     addl $16,%esp
     fldl .LC1
     fsubp %st,%st(1)
     fldl .LC1
     faddp %st,%st(1)
     fstpl -16(%ebp)
     addl $-8,%esp
     fldl -8(%ebp)
     subl $8,%esp
     fstpl (%esp)
     call my_sqr
     addl $16,%esp
     fstpl -24(%ebp)
     fldl .LC1
     fsubl -24(%ebp)
     fldl .LC1
     faddp %st,%st(1)
     fstpl -24(%ebp)
     fldl -16(%ebp)
     fsubl -24(%ebp)
     fabs
     fstpl -32(%ebp)
     addl $-4,%esp
     fldl -16(%ebp)
     subl $8,%esp
     fstpl (%esp)
     pushl $.LC2
     call printf
     addl $16,%esp
     addl $-4,%esp
     fldl -24(%ebp)
     subl $8,%esp
     fstpl (%esp)
     pushl $.LC3
     call printf
     addl $16,%esp
     addl $-4,%esp
     fldl -32(%ebp)
     subl $8,%esp
     fstpl (%esp)
     pushl $.LC4
     call printf
     addl $16,%esp
     movl $1,%eax
     jmp .L3
     .p2align 4,,7
.L3:
     movl %ebp,%esp
     popl %ebp
     ret
.Lfe2:
     .size      main,.Lfe2-main
     .ident    "GCC: (GNU) 2.95.2 19991024 (release)"