[x265] Interested in fast popcnt substitute below SSE4.2?

[Mario *LigH* Rohkrämer]

Another point of view on this matter:

http://danluu.com/assembly-intrinsics/

Seems to relativate the impact.

I don't know if you already knew about all this before...


Am 22.02.2017, 13:39 Uhr, schrieb Mario *LigH* Rohkrämer <contact at ligh.de>:

> http://wm.ite.pl/articles/sse-popcount.html
>
> May even be faster than the popcnt instruction implemented in a  
> supporting CPU!
>
> Found via a German "conspiracy news" blog (no, that's not at all meant  
> seriously) which sometimes also mentions computer security issues and  
> interesting programming challenges: https://blog.fefe.de/?ts=a653b91f
>


-- 

Fun and success!
Mario *LigH* Rohkrämer
mailto:contact at ligh.de