s

loop:    movd        mm0, [esi]    punpcklbw   mm0, mm7    movd        mm2, [esi + ebx]    punpcklbw   mm2, mm7    paddusw     mm4, mm2    psubusw     mm4, mm0    movq        mm6, mm4    psrlw       mm6, mm3    packuswb    mm6, mm7    movd        [edi], mm6    paddusw     mm4, mm2    psubusw     mm4, mm0    add         edi, eax                                    add         esi, 4    sub         ecx, 1    jnz         loop