Re: [PATCH] x86: introduce and use percpu_inc()

[Jan Beulich]

>>> "H. Peter Anvin"  04/21/10 7:57 PM >>>
>On 04/21/2010 07:21 AM, Jan Beulich wrote:
>> ... generating slightly smaller code.
>> 
>> Signed-off-by: Jan Beulich 
>
>How much smaller?

The percpu_add(..., 1) -> percpu_inc() conversion is just a single
byte reduction (the immediate operand of the add); the other one
(where percpu_...() wasn't even used) is certainly a bigger win
(most of which obviously could also be achieved using percpu_add()).

>Keep in mind that although INC is smaller than ADD,
>the former has flag dependencies that the latter doesn't...

Wasn't that a problem just on Pentium4-s, which when I submitted
another related patch a couple of months back I was told would
not be a primary target anymore?

Jan

--
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/