Re: [Boost-users] boost.proto optimization on MSVC (2005/2008)

From: AJD (n.outpost_at_[hidden])
Date: 2007-12-06 22:27:30

AJD <n.outpost <at> gmail.com> writes:

> Here's some of the generated assembly:
> 
> int main()
> {
> 00401800  sub         esp,18h
>         vector2< float[3] > v1 = { 0, 1, 2 };
> 00401803  xorps       xmm0,xmm0
>         vector2< float[3] > v2 = { 3, 4, 5 };
>         vector2< float[3] > v3 = { 6, 7, 8 };
> 
>         // Add two vectors lazily and get the 2nd element.
> #if 1
>         // this sticks temporary junk all over the stack, even with 2 terms
>         std::cout << (v1 + v2)[0];
> 00401806  fld         dword ptr [__real <at> 40400000 (402128h)]
> 0040180C  movss       dword ptr [esp],xmm0
> 00401811  movss       xmm0,dword ptr [__real <at> 3f800000 (402124h)]
> 00401819  movss       dword ptr [esp+4],xmm0
> 0040181F  movss       xmm0,dword ptr [__real <at> 40000000 (402120h)]
> 00401827  movss       dword ptr [esp+8],xmm0
> 0040182D  movss       xmm0,dword ptr [__real <at> 40400000 (402128h)]
> 00401835  movss       dword ptr [esp+0Ch],xmm0
> 0040183B  movss       xmm0,dword ptr [__real <at> 40800000 (40211Ch)]
> 00401843  push        ecx
> 00401844  mov         ecx,dword ptr [__imp_std::cout (402044h)]
> 0040184A  fstp        dword ptr [esp]
> 0040184D  movss       dword ptr [esp+14h],xmm0
> 00401853  movss       xmm0,dword ptr [__real <at> 40a00000 (402118h)]
> 0040185B  movss       dword ptr [esp+18h],xmm0
> 00401861  call        dword ptr
> [__imp_std::basic_ostream<char,std::char_traits<char> >::operator<< 
> (402040h)]
> 
>         std::cin.get();
> 00401867  mov         ecx,dword ptr [__imp_std::cin (40203Ch)]
> 0040186D  call        dword ptr
> [__imp_std::basic_istream<char,std::char_traits<char> >::get (402038h)]
> 
>         return 0;
> 00401873  xor         eax,eax
> }
> 00401875  add         esp,18h
> 00401878  ret
> 

Just to be clear, the following is the expected assembly:

00401800  fld         dword ptr [__real_at_41100000 (402118h)] 
00401806  push        ecx  
00401807  mov         ecx,dword ptr [__imp_std::cout (402044h)] 
0040180D  fstp        dword ptr [esp] 
00401810  call        dword ptr
[__imp_std::basic_ostream<char,std::char_traits<char> >::operator<< (402040h)] 
00401816  mov         ecx,dword ptr [__imp_std::cin (40203Ch)] 
0040181C  call        dword ptr
[__imp_std::basic_istream<char,std::char_traits<char> >::get (402038h)] 
00401822  xor         eax,eax 
00401824  ret        

Notice how in both versions the actual printed value is folded as a constant at
compile-time, loaded onto the stack through the fp instructions, and printed. In
the first version of course all that extra data (the vectors) is being copied
onto the stack through xmm0, and this data is never touched.