[llvm-dev] Where's the optimiser gone? (part 5.c): missed tail calls, and more...

[Stefan Kanthak via llvm-dev]

Compile the following functions with "-O3 -target i386-win32"
(see <https://godbolt.org/z/exmjWY>):

__int64 __fastcall div(__int64 foo, __int64 bar)
{
    return foo / bar;
}


On the left the generated code; on the right the expected,
properly optimised code:

    push  dword ptr [esp + 16]        |
    push  dword ptr [esp + 16]        |
    push  dword ptr [esp + 16]        |
    push  dword ptr [esp + 16]        |
    call  __alldiv                    |     jmp  __alldiv
    ret   16                          |


__int64 __fastcall mod(__int64 foo, __int64 bar)
{
    return foo % bar;
}

    push  dword ptr [esp + 16]        |
    push  dword ptr [esp + 16]        |
    push  dword ptr [esp + 16]        |
    push  dword ptr [esp + 16]        |
    call  __allrem                    |     jmp  __allrem
    ret   16                          |


__int64 __fastcall mul(__int64 foo, __int64 bar)
{
    return foo * bar;
}

    push  esi                         |     mov   ecx, dword ptr [esp + 16]
    mov   ecx, dword ptr [esp + 16]   |     mov   edx, dword ptr [esp + 12]
    mov   esi, dword ptr [esp + 8]    |     imul  edx, dword ptr [esp + 8]
    mov   eax, ecx                    |     mov   eax, dword ptr [esp + 4]
    imul  ecx, dword ptr [esp + 12]   |     imul  ecx, eax
    mul   esi                         |     add   ecx, edx
    imul  esi, dword ptr [esp + 20]   |     mul   dword ptr [esp + 12]
    add   edx, ecx                    |     add   edx, ecx
    add   edx, esi                    |     ret   16
    pop   esi                         |
    ret   16                          |