Code for Light without DirectX... :)

Light_Flash3 PROC x1:DWORD, y1:DWORD, lum:DWORD, src:DWORD, des:DWORD
    LOCAL mx:DWORD, my:DWORD, x2:DWORD, y2:DWORD, tff:DWORD
    mov eax,lum
    shr eax,1                  ; Light_Flash: dynamic 2D lighting routine
    mov lum,eax                ; does not uses any pre-computed data
    mov tff,255                ; ie. pure light frum tha melting cpu core :)
    mov eax,maxx
    mov mx,eax
    mov eax,maxy
    dec eax
    mov my,eax
    mov esi,src
    mov edi,des
    xor eax,eax
    mov y2,eax
ylp3:                          ; 2x2 instead of per pixel lighting 
    xor eax,eax                ; half the quality, but higher speed
    mov x2,eax
xlp3:
    mov eax,y2
    sub eax,y1
    imul eax
    mov ebx,x2
    sub ebx,x1
    imul ebx,ebx
    add eax,ebx
    mov edx,lum
    imul edx,edx
    xor ebx,ebx
    cmp eax,edx
    ja @F                      ; jump to end causes time waves
    push eax
    fild dword ptr[esp]
    fsqrt
    fidiv lum                  ; this code is -different-
    fld1
    fsubrp st(1),st(0)
    fmul st(0),st(0)           ; curve
    fmul st(0),st(0)           ; curve
    fimul tff
    fistp dword ptr[esp]

    pop ebx
    imul ebx,01010101h
@@:
    mov eax,y2
    imul maxx
    add eax,x2
    lea eax,[eax+eax*2]
    mov edx,maxx
    lea edx,[edx+edx*2]
    add edx,eax
    
    movd MM2,ebx               ; simply add with saturation
    movq MM0,[esi+eax]         ; gamma correction is against this code
    psllq MM2,32
    movq MM1,[esi+edx]
    movd MM3,ebx
    por MM2,MM3
    paddusb MM0,MM2
    movd [edi+eax],MM0
    paddusb MM1,MM2
    psrlq MM0,32
    movd [edi+edx],MM1
    movd ebx,MM0
    psrlq MM1,32
    mov [edi+eax+4],bx
    movd ecx,MM1
    mov [edi+edx+4],cx
    emms
@@:
    mov eax,x2
    add eax,2
    mov x2,eax
    cmp eax,mx
    jbe xlp3
    mov eax,y2
    add eax,2
    mov y2,eax
    cmp eax,my
    jbe ylp3
    ret
Light_Flash3 ENDP