The mapping after we have the leading 1's count can be done in 3 instructions (in 32-bit math) on either x86 or ARM:
t = 0x2020c6 >> x
return (t << (t & 31)) >> 27 t = 0x2020c6 >> x
return (t << (t & 31)) >> 27 return (0x43201 >> x*4) & 7
mov eax, 0x2020c6
shr eax, cl
mov cl, al
shl eax, cl
shr eax, 27
mov ax, 0x4681
lea ecx, [ecx+ecx*2]
shr eax, cl
and eax, 7
lzcnt ecx,ecx
mov eax, 00100 0011 0010 0000 0001b shl ecx,2 shrx eax,eax,ecx and eax,15