foreach is slower than for?

[Stanislav Blinov]

I was wondering about it for some time:

void foreach_loop(int arr[100])
{
     foreach(i,a; arr)
     {
         auto e = a;
     }
}

void for_loop(int arr[100])
{
     for (int i = 0; i < 100; ++i)
     {
         auto e = arr[i];
     }
}


compiled with -O -release yields this:

.text.void main.foreach_loop(int[100])  segment
         assume  CS:.text.void main.foreach_loop(int[100])
void main.foreach_loop(int[100]):
                 push    EBP
                 mov     EBP,ESP
                 sub     ESP,8
                 mov     EAX,064h
                 lea     ECX,8[EBP]
                 xor     EDX,EDX
                 mov     -8[EBP],EAX
                 mov     -4[EBP],ECX
                 cmp     -8[EBP],EDX
                 je      L23
L1B:            add     EDX,1
                 cmp     EDX,-8[EBP]
                 jb      L1B
L23:            mov     ESP,EBP
                 pop     EBP
                 ret     0190h
                 nop
                 nop
                 nop
.text.void main.foreach_loop(int[100])  ends
.text.void main.for_loop(int[100])      segment
         assume  CS:.text.void main.for_loop(int[100])
void main.for_loop(int[100]):
                 push    EBP
                 mov     EBP,ESP
                 xor     EAX,EAX
L5:             inc     EAX
                 cmp     EAX,064h
                 jb      L5
                 pop     EBP
                 ret     0190h
                 nop
.text.void main.for_loop(int[100])      ends

Without -O -release the difference is even greater

Is this normal? I mean, shouldn't the compiler optimize foreach a bit 
more? Or is it that I simply misunderstand generated code?