Re: [Xen-devel] [PATCH] xen/arm: minor improvement in smp_send_call_function_mask()

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

On 21/08/14 17:54, Julien Grall wrote:
> Hi Anup,
>
> On 21/08/14 06:04, Anup Patel wrote:
>>> The best alternative would be cpumask_empty.
>>
>> All three cpumask_empty(), cpumask_first(), and cpumask_weight()
>> are O(N) where N is number of bits in cpumask.
>> It really does not make much difference which of these operation
>> is chosen.

They are all O(N), but O() notation hides lesser factors.

cpumask_empty() is slightly cheaper than cpumask_first(), which are both
substantially cheaper than cpumask_weight().

There is no fastpath for calculating the hamming weight of 0, resulting
in a lot of dependent shift/mask operations.

~Andrew

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel