optimization/10772: Result differences between debug and optmize libs on linux; and with sol/nt on optimize mode

[omar beo]

Hi,
This problem could be related to the Rounding as many suggested, but how 
come I got different numbers between debug and optimize libs when I run on 
linux?
Why this code generates the same numbers on NT and Unix, but not on linux?

Unfortunately, I wasnÂ’t able to create an identical test case to the one i'm 
currently testing, probably because this behavior only happened when you run 
a large application and not just a small test case.
But i included a simalr test case with a similar behavior.

Could you look at the assembly code generated on debug and optimize mode, 
and tell me if they are equivalent. Because they don't produce the same 
numbers .

Thank you.


Here the C++ code:

double this->factor;
int this->GetP() {}
int object::GetPS() {}

double this->factor;
int this->GetP() {}
int object::GetPS()
{
double aa = (double)this->GetP() * this->factor;
int bb = (int) aa;
return bb;
}

Here the Assembly code generated in linux in optimize mode (O3):
===================
.LFE223:
.Lfe223:
        .size   _ZN17object9GetPSEv,.Lfe223-_ZN17object9GetPSEv
        .align 2
        .p2align 4,,15
.globl _ZN17object13GetPSEv
        .type   _ZN17object13GetPSEv,@function
_ZN17object13GetPSEv:
.LFB224:
        pushl   %ebp
.LCFI739:
        movl    %esp, %ebp
.LCFI740:
        subl    $24, %esp
.LCFI741:
        movl    %ebx, -4(%ebp)
.LCFI742:
        movl    8(%ebp), %ebx
        movl    (%ebx), %eax
        movl    %ebx, (%esp)
        call    *220(%eax)
        pushl   %eax
        fildl   (%esp)
        addl    $4, %esp
        fmull   116(%ebx)
        fnstcw  -6(%ebp)
        movl    -4(%ebp), %ebx
        movzwl  -6(%ebp), %eax
        orw     $3072, %ax
        movw    %ax, -8(%ebp)
        fldcw   -8(%ebp)
        fistpl  -12(%ebp)
        fldcw   -6(%ebp)
        movl    -12(%ebp), %eax
        movl    %ebp, %esp
        popl    %ebp
        ret
.LFE224:
.Lfe224:
        .size   _ZN17object13GetPSEv,.Lfe224-_ZN1object13GetPSEv7
        .align 2
        .p2align 4,,15

===================
Here the Assembly code generated in linux in optimize mode (O3):

.LFE183:
.Lfe183:
        .size   _ZN17object9GetPSEv,.Lfe183-_ZN17object9GetPSEv
        .align 2
.globl _ZN17object13GetPSEv
        .type   _ZN17object13GetPSEv,@function
_ZN17object13GetPSEv:
.LFB184:
        .loc 1 5737 0
.LBB414:
        pushl   %ebp
.LCFI554:
        movl    %esp, %ebp
.LCFI555:
        subl    $24, %esp
.LCFI556:
        .loc 1 5739 0
        movl    8(%ebp), %eax
        movl    (%eax), %edx
        addl    $220, %edx
        movl    8(%ebp), %eax
        movl    %eax, (%esp)
        movl    (%edx), %eax
        call    *%eax
        pushl   %eax
        fildl   (%esp)
        leal    4(%esp), %esp
        movl    8(%ebp), %eax
        fmull   116(%eax)
        fstpl   -8(%ebp)
        .loc 1 5740 0
        fldl    -8(%ebp)
        fnstcw  -14(%ebp)
        movzwl  -14(%ebp), %eax
        orw     $3072, %ax
        movw    %ax, -16(%ebp)
        fldcw   -16(%ebp)
        fistpl  -12(%ebp)
        fldcw   -14(%ebp)
        .loc 1 5741 0
        movl    -12(%ebp), %eax
.LBE414:
        pushl   %ebp
.LCFI554:
        movl    %esp, %ebp
        .loc 1 5742 0
        leave
        ret
.LFE184:
.Lfe184:



i was able to create a test case that shows the same behavior:

----
#include <stdio.h>
#include <stdlib.h>


double tt = 0.000000005975;

double afunction()
{
  return (5.975e-9);
}


long getS()
{
  return 3332;
}

long getP()
{
  return 6665;
}

double getPSFactor()
{
  return ( (double) getS() / (double) getP());
}


int main(int argc, char* argv[])
{

double temp = 1e12*afunction();
long var_1 = (long)temp;
long var_2 = (long)(1e12*afunction()) ;
long var_3 = (long)(1e12*5.975e-9) ;
double temp1 = tt;
long var_4 = (long)(1e12*temp1) ;
long var_5 = (long) (1e12*tt+0.5) ;
printf("var_1: %08d\n", var_1);
printf("var_2: %08d\n", var_2);
printf("var_3: %08d\n", var_3);
printf("var_4: %08d\n", var_4);
printf("var_5: %08d\n", var_5);

  return 0;
}


---


results using:
linux: debug libs
var_1: 00005975
var_2: 00005974
var_3: 00005975
var_4: 00005974
var_5: 00005975

linux opt libs:
var_1: 00005975
var_2: 00005975
var_3: 00005975
var_4: 00005974
var_5: 00005975

sol/nt:
var_1: 00005975
var_2: 00005975
var_3: 00005975
var_4: 00005975
var_5: 00005975

_________________________________________________________________
Help STOP SPAM with the new MSN 8 and get 2 months FREE*  
http://join.msn.com/?page=features/junkmail