Re: [PATCH v2 10/30] Add x86-specific parity functions

[One Thousand Gnomes]

On Wed, 06 Apr 2016 12:45:27 -0700
Andi Kleen <andi@xxxxxxxxxxxxxx> wrote:

> zengzhaoxiu@xxxxxxx writes:
> 
> > From: Zhaoxiu Zeng <zhaoxiu.zeng@xxxxxxxxx>
> >
> > Use alternatives, lifted from arch_hweight  
> 
> Is there actually anything performance critical in the kernel that uses
> parity?

On very low end devices some of the flash, but the implementation here is
ironically pretty much worst-case for such x86 devices 8)

Alan