On Wed, Jun 13, 2012 at 2:08 PM, Michael Cree <mcree@xxxxxxxxxxxx> wrote:
>
> From commit 36126f8f2ed8 prep_zero_mask() must, and I quote, "generate
> an *exact* mask of which byte had the first zero."
No, that wasn't the intent. It must generate something that can be
or'ed together so that the "generate_zero_mask()" can actually then
generate the mask itself.
It has to be exact in the sense that the value must *exactly* imply
the first byte. That's different from the "has_zero()" function that
doesn't need to calculate which is the *first* byte with the zero,
just that there is at least one byte of zero.
In fact, look at the x86 implementation. The prep_zero_mask() function
is a no-op, because it just leaves the high bit set in the appropriate
byte. The actual bytemask is generated by create_zero_mask().
Linus
--
To unsubscribe from this list: send the line "unsubscribe linux-arch" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
