optimized itoa function

Question

I am thinking on how to implement the conversion of an integer (4byte, unsigned) to string with SSE instructions. The usual routine is to divide the number and store it in a loc

Answer 1

That's part of my code in asm. It works only for range 255-0 It can be faster however here you can find direction and main idea.

4 imuls 1 memory read 1 memory write

You can try to reduce 2 imule's and use lea's with shifting. However you can't find anything faster in C/C++/Python ;)

void itoa_asm(unsigned char inVal, char *str)
{
    __asm
    {
        // eax=100's      -> (some_integer/100) = (some_integer*41) >> 12
        movzx esi,inVal
        mov eax,esi
        mov ecx,41
        imul eax,ecx
        shr eax,12

        mov edx,eax
        imul edx,100
        mov edi,edx

        // ebx=10's       -> (some_integer/10) = (some_integer*205) >> 11
        mov ebx,esi
        sub ebx,edx
        mov ecx,205
        imul ebx,ecx
        shr ebx,11

        mov edx,ebx
        imul edx,10

        // ecx = 1
        mov ecx,esi
        sub ecx,edx    // -> sub 10's
        sub ecx,edi    // -> sub 100's

        add al,'0'
        add bl,'0'
        add cl,'0'
        //shl eax,
        shl ebx,8
        shl ecx,16
        or eax,ebx
        or eax,ecx

        mov edi,str
        mov [edi],eax

    }

}