1.28. 64-BIT VALUES IN 32-BIT ENVIRONMENT
push ebx
mov edx, DWORD PTR [esp+8]
mov eax, DWORD PTR [esp+16]
mov ebx, DWORD PTR [esp+12]
mov ecx, DWORD PTR [esp+20]
imul ebx, eax
imul ecx, edx
mul edx
add ecx, ebx
add edx, ecx
pop ebx
ret_f_div:
sub esp, 28
mov eax, DWORD PTR [esp+40]
mov edx, DWORD PTR [esp+44]
mov DWORD PTR [esp+8], eax
mov eax, DWORD PTR [esp+32]
mov DWORD PTR [esp+12], edx
mov edx, DWORD PTR [esp+36]
mov DWORD PTR [esp], eax
mov DWORD PTR [esp+4], edx
call ___udivdi3 ; unsigned division
add esp, 28
ret
_f_rem:
sub esp, 28
mov eax, DWORD PTR [esp+40]
mov edx, DWORD PTR [esp+44]
mov DWORD PTR [esp+8], eax
mov eax, DWORD PTR [esp+32]
mov DWORD PTR [esp+12], edx
mov edx, DWORD PTR [esp+36]
mov DWORD PTR [esp], eax
mov DWORD PTR [esp+4], edx
call ___umoddi3 ; unsigned modulo
add esp, 28
ret
GCC does the expected, but the multiplication code is inlined right in the function, thinking it could be
more efficient. GCC has different library function names:.4 on page 1043.
ARM
Keil for Thumb mode inserts library subroutine calls:
Listing 1.379: Optimizing Keil 6/2013 (Thumb mode)||f_mul|| PROC
PUSH {r4,lr}
BL __aeabi_lmul
POP {r4,pc}
ENDP
||f_div|| PROC
PUSH {r4,lr}
BL __aeabi_uldivmod
POP {r4,pc}
ENDP
||f_rem|| PROC
PUSH {r4,lr}
BL __aeabi_uldivmod
MOVS r0,r2
MOVS r1,r3
POP {r4,pc}
ENDP