floating-WTF

[sclytrack]

Yes, I missed my lessons in clear communication.


-------------------------------------------------
+	The complete source files.
-------------------------------------------------

import std.stdio;

void calculate1(float a, float b)
{
	float s1 = 1.0f - a;
	float s2 = a * b;
	writeln(s2);
	writeln(a * b);
}

void calculate2(float a, float b)
{
	float s1 = 1.0 - a;
	float s2 = a * b;
	writeln(s2);
	writeln(a * b);
}

void calculate3(double a, double b)
{
	double s1 = 1.0 - a;
	double s2 = a * b;
	writeln(s2);
	writeln(a * b);	
}

int main()
{	
	writeln("calculate1:");
	calculate1(0.75f,2.0f);
	writeln("calculate2:");
	calculate2(0.75f,2.0f);
	writeln("calculate3:");
	calculate3(0.75f,2.0f);
	return 0;
}

-------------------------------------------------
+	The complete output
-------------------------------------------------

calculate1:
1.5
1.5
calculate2:
0
1.5
calculate3:
1.5
1.5

-------------------------------------------------
+	Compiler
-------------------------------------------------

DMD64 D Compiler v2.057
Copyright (c) 1999-2011 by Digital Mars written by Walter Bright
Documentation: http://www.digitalmars.com/d/2.0/index.html
Usage:

This is from the downloaded zip file.
I'm using eclipse to compile it. Added the -debug.


-------------------------------------------------
+	Ubuntu 11.10 64 bit
-------------------------------------------------

uname -r
3.0.0-15-generic

-------------------------------------------------
+	BEHAVIOUR
-------------------------------------------------

As for the behaviour on 32 bit. I wish
somebody else would do it. :-)

In the previous message here below is the assembly
output of calculate2. Pay close attention to the
cvtss2sd, the cvtsd2ss and the mulss.

	float s1 = 1.0 - a;
	float s2 = a * b;

It converts the float a to double precision.
then performs the s1 calculation.

Then does the s2 calculation with the high
precision a and the normal float b.

Also it performs the "cvtsd2ss %xmm2,%xmm2"
for no reason at all. As it is no longer used
in the rest the code.

-------------------------------------------------
+	objdump -S test1.o
-------------------------------------------------

0000000000000000 <_D4main10calculate2FffZv>:
    0:	55                   	push   %rbp
    1:	48 8b ec             	mov    %rsp,%rbp
    4:	48 83 ec 20          	sub    $0x20,%rsp
    8:	f3 0f 11 45 f0       	movss  %xmm0,-0x10(%rbp)
    d:	f3 0f 11 4d f8       	movss  %xmm1,-0x8(%rbp)
   12:	48 b8 00 00 00 00 00 	movabs $0x3ff0000000000000,%rax
   19:	00 f0 3f
   1c:	48 89 45 e0          	mov    %rax,-0x20(%rbp)
   20:	f2 0f 10 55 e0       	movsd  -0x20(%rbp),%xmm2
   25:	f3 0f 5a c9          	cvtss2sd %xmm1,%xmm1
   29:	f2 0f 5c d1          	subsd  %xmm1,%xmm2
   2d:	f2 0f 5a d2          	cvtsd2ss %xmm2,%xmm2
   31:	f3 0f 59 c8          	mulss  %xmm0,%xmm1
   35:	f3 0f 11 4d e8       	movss  %xmm1,-0x18(%rbp)
   3a:	f3 0f 10 45 e8       	movss  -0x18(%rbp),%xmm0
   3f:	e8 00 00 00 00       	callq  44 <_D4main10calculate2FffZv+0x44>
   44:	f3 0f 10 45 f8       	movss  -0x8(%rbp),%xmm0
   49:	f3 0f 10 4d f0       	movss  -0x10(%rbp),%xmm1
   4e:	f3 0f 59 c1          	mulss  %xmm1,%xmm0
   52:	e8 00 00 00 00       	callq  57 <_D4main10calculate2FffZv+0x57>
   57:	c9                   	leaveq
   58:	c3                   	retq
   59:	90                   	nop
   5a:	90                   	nop
   5b:	90                   	nop


I'm going to eat now.



On 01/24/2012 05:01 PM, dennis luehring wrote:
> can you give us a complete out-of-the-box compileable example (with
> imports,main,etc.) with both examples the working/and nonworking
>
> does it work correct with dmd(32bit)?
>
> is this "calculate2" needed to reproduce the behavior?
>
> and what compiler did you test: dmd64, (dmd32?), ...?
>
> Am 24.01.2012 16:20, schrieb sclytrack:
>>
>>
>> void calculate2(float a, float b)
>> {
>> float s1 = 1.0 - a;
>> float s2 = a * b;
>> writeln(s2);
>> writeln(a * b);
>> }
>>
>> ----------------
>> Output:
>> t*b= 0
>> t*b= 1.5
>> ----------------
>>
>>
>> assume CS:.text._D4main10calculate2FffZv
>> _D4main10calculate2FffZv:
>> push RBP
>> mov RBP,RSP
>> sub RSP,020h
>> movss -010h[RBP],XMM0
>> movss -8[RBP],XMM1
>> mov RAX,03FF0000000000000h
>> mov -020h[RBP],RAX
>> movsd XMM2,-020h[RBP]
>> cvtss2sd XMM1,XMM1
>> subsd XMM2,XMM1
>> ------conversion but xmm2 is no longer used
>> cvtsd2ss XMM2,XMM2
>> ------precision error multiplication
>> mulss XMM1,XMM0
>> movss -018h[RBP],XMM1
>> movss XMM0,-018h[RBP]
>> call _D3std5stdio14__T7writelnTfZ7writelnFfZv at PC32
>> movss XMM0,-8[RBP]
>> movss XMM1,-010h[RBP]
>> mulss XMM0,XMM1
>> call _D3std5stdio14__T7writelnTfZ7writelnFfZv at PC32
>> leave
>> ret
>> nop
>> nop
>> nop
>>
>> ------------
>> DMD64 D Compiler v2.057
>> Ubuntu 11.10
>