Re: [PATCH 2/2] The new jhash implementation

[Eric Dumazet]

Le jeudi 25 novembre 2010 Ã 21:55 +0800, Changli Gao a Ãcrit :

> > I suggest :
> >
> > #include <linux/unaligned/packed_struct.h>
> > ...
> >        a += __get_unaligned_cpu32(k);
> >        b += __get_unaligned_cpu32(k+4);
> >        c += __get_unaligned_cpu32(k+8);
> >
> > Fits nicely in registers.
> >
> 
> I think you mean get_unaligned_le32().
> 

No, I meant __get_unaligned_cpu32()

We do same thing in jhash2() :

	a += k[0]; 
	b += k[1];
	c += k[2];

We dont care of bit order of the 32bit quantity we are adding to a,b or
c , as long its consistent for the current machine ;)

get_unaligned_le32() would be slow on big endian arches.



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/