So are you proud of me?  :-)

memcpy is designed to copy from a buffer to another buffer, for
a length of whatever.  No overrun allowed.  Destination to be
returned to caller.  Parameter order is dest, source, length...

; stringa.asm - string assembler functions
; 
; This program written by Paul Edwards, Fidonet 3:711/934
; Released to the public domain

.386p

.model flat

_DATA   segment dword public use32 "DATA"
_DATA   ends
_BSS    segment dword public use32 "BSS"
_BSS    ends

DGROUP  group   _DATA,_BSS
    assume cs:_TEXT,ds:DGROUP

_TEXT segment "CODE"

public memcpy
memcpy proc 
push ebp
mov ebp, esp
pushf
push edi
push esi
push ecx
mov edi, [ebp+8]
mov esi, [ebp+12]
mov ecx, [ebp+16]
cld
shr ecx, 2
rep movsd
mov ecx, [ebp+16]
and ecx, 00000003H
rep movsb
mov eax, [ebp+8]
pop ecx
pop esi
pop edi
popf
pop ebp
ret
memcpy endp

_TEXT ends
          
end
@EOT:

---