[soc] - asm no delphi

function FastCharMove(parametro1; parametro2; parametro3);
asm
  // O Delphi põe os parâmetros automaticamente assim:
  // ECX = parametro1
  // EAX = parametro2
  // EDX = parametro3
  // Qnd tem mais de 3 parâmetros, eles são passados na stack
  // O resultado da função tem um registrador específico, mas eu esqueci
end;

//My move is not as fast as MOVE when source and destination are both
//DWord aligned, but certainly faster when they are not.
//As we are moving characters in a string, it is not very likely at all that
//both source and destination are DWord aligned, so moving bytes avoids the
//cycle penality of reading/writing DWords across physical boundaries
procedure FastCharMove(const Source; var Dest; Count : Integer);
asm
//Note:  When this function is called, delphi passes the parameters as follows
//ECX = Count
//EAX = Const Source
//EDX = Var Dest

        //If no bytes to copy, just quit altogether, no point pushing registers
        cmp   ECX,0
        Je    @JustQuit

        //Preserve the critical delphi registers
        push  ESI
        push  EDI

        //move Source into ESI  (generally the SOURCE register)
        //move Dest into EDI (generally the DEST register for string commands)
        //This may not actually be neccessary, as I am not using MOVsb etc
        //I may be able just to use EAX and EDX, there may be a penalty for
        //not using ESI, EDI but I doubt it, this is another thing worth trying !
        mov   ESI, EAX
        mov   EDI, EDX

        //The following loop is the same as repNZ MovSB, but oddly quicker !
    @Loop:
        //Get the source byte
        Mov   AL, [ESI]
        //Point to next byte
        Inc   ESI
        //Put it into the Dest
        mov   [EDI], AL
        //Point dest to next position
        Inc   EDI
        //Dec ECX to note how many we have left to copy
        Dec   ECX
        //If ECX <> 0 then loop
        Jnz   @Loop

        //Another optimization note.
        //Many people like to do this

        //Mov AL, [ESI]
        //Mov [EDI], Al
        //Inc ESI
        //Inc ESI

        //There is a hidden problem here, I wont go into too much detail, but
        //the pentium can continue processing instructions while it is still
        //working out the result of INC ESI or INC EDI
        //(almost like a multithreaded CPU)
        //if, however, you go to use them while they are still being calculated
        //the processor will stop until they are calculated (a penalty)
        //Therefore I alter ESI and EDI as far in advance as possible of using them

        //Pop the critical Delphi registers that we have altered
        pop   EDI
        pop   ESI
    @JustQuit:
end;