GeezerVison

(gdb) disassemble __popcountdi2 
Dump of assembler code for function __popcountdi2:
   0x00007fffeaa997c0 <+0>:	endbr64 
   0x00007fffeaa997c4 <+4>:	movabs rdx,0x5555555555555555
   0x00007fffeaa997ce <+14>:	mov    rax,rdi
   0x00007fffeaa997d1 <+17>:	shr    rax,1
   0x00007fffeaa997d4 <+20>:	and    rax,rdx
   0x00007fffeaa997d7 <+23>:	movabs rdx,0x3333333333333333
   0x00007fffeaa997e1 <+33>:	sub    rdi,rax
   0x00007fffeaa997e4 <+36>:	mov    rax,rdi
   0x00007fffeaa997e7 <+39>:	shr    rdi,0x2
   0x00007fffeaa997eb <+43>:	and    rax,rdx
   0x00007fffeaa997ee <+46>:	and    rdi,rdx
   0x00007fffeaa997f1 <+49>:	add    rdi,rax
   0x00007fffeaa997f4 <+52>:	mov    rax,rdi
   0x00007fffeaa997f7 <+55>:	shr    rax,0x4
   0x00007fffeaa997fb <+59>:	add    rax,rdi
   0x00007fffeaa997fe <+62>:	movabs rdi,0xf0f0f0f0f0f0f0f
   0x00007fffeaa99808 <+72>:	and    rax,rdi
   0x00007fffeaa9980b <+75>:	movabs rdi,0x101010101010101
   0x00007fffeaa99815 <+85>:	imul   rax,rdi
   0x00007fffeaa99819 <+89>:	shr    rax,0x38
   0x00007fffeaa9981d <+93>:	ret    
End of assembler dump.

popcnt ecx,ecx

    /* We could use native popcount instruction but that would
       require to either add configure flags to enable SSE4.2
       support or to detect it dynamically.  Otherwise, we have
       a risk of CPython not working properly on older hardware.

       In practice, there's no observable difference in
       performance between using a popcount instruction or the
       following fallback code.

       The algorithm is copied from:
       https://graphics.stanford.edu/~seander/bithacks.html
    */